forked from rufuspollock-okfn/bibserver
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathref_all.bib
executable file
·2791 lines (2631 loc) · 204 KB
/
ref_all.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@Article{ citeulike:6545194,
abstract = "Web documents are available in various forms, most of which do not carry additional semantics. This paper presents a model for general document metadata extraction. The model, which combines segmentation by keywords and pattern matching techniques, was implemented using PHP, MySQL, JavaScript and HTML. The system was tested with 40 randomly selected PDF documents (mainly theses). An evaluation of the system was done using standard criteria measures namely precision, recall, accuracy and F-measure. The results show that the model is relatively effective for the task of metadata extraction, especially for theses and dissertations. A combination of machine learning with these rule-based methods will be explored in the future for better results. 10.1177/0165551509105195",
author = "Bolanle {Adefowoke Ojokoh} and Olumide {Sunday Adewale} and Samuel {Oluwole Falaki}",
citeulike-article-id = "6545194",
citeulike-linkout-0 = "http://dx.doi.org/10.1177/0165551509105195",
citeulike-linkout-1 = "http://jis.sagepub.com/cgi/content/abstract/35/5/563",
day = "1",
doi = "10.1177/0165551509105195",
journal = "Journal of Information Science",
month = "October",
number = "5",
pages = "563--570",
posted-at = "2010-01-15 20:48:09",
priority = "2",
title = "Automated document metadata extraction",
url = "http://dx.doi.org/10.1177/0165551509105195",
volume = "35",
year = "2009"
}
@Book{ citeulike:273980,
abstract = "{The development of the Semantic Web, with machine-readable content, has the potential to revolutionize the World Wide Web and its use. <i>A Semantic Web Primer</i> provides an introduction and guide to this emerging field, describing its key ideas, languages, and technologies. Suitable for use as a textbook or for self-study by professionals, it concentrates on undergraduate-level fundamental concepts and techniques that will enable readers to proceed with building applications on their own. It includes exercises, project descriptions, and annotated references to relevant online materials. A Semantic Web Primer is the only available book on the Semantic Web to include a systematic treatment of the different languages (XML, RDF, OWL, and rules) and technologies (explicit metadata, ontologies, and logic and inference) that are central to Semantic Web development. The book also examines such crucial related topics as ontology engineering and application scenarios.<br /> <br /> After an introductory chapter, topics covered in succeeding chapters include XML and related technologies that support semantic interoperability; RDF and RDF Schema, the standard data model for machine-processable semantics; and OWL, the W3C-approved standard for a Web ontology language more extensive than RDF Schema; rules, both monotonic and nonmonotonic, in the framework of the Semantic Web; selected application domains and how the Semantic Web would benefit them; the development of ontology-based systems; and current debates on key issues and predictions for the future.}",
author = "Grigoris Antoniou and Frank {van Harmelen}",
citeulike-article-id = "273980",
howpublished = "Hardcover",
isbn = "0262012103",
keywords = "semantic\_web",
month = "April",
posted-at = "2009-06-30 19:51:07",
priority = "2",
publisher = "{The MIT Press}",
title = "A Semantic Web Primer (Cooperative Information Systems)",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0262012103",
year = "2004"
}
@Article{ citeulike:4149298,
abstract = "In the age of digital information more and more digital libraries and historical archives are using information systems in order to facilitate the document retrieval and provide better visualization of the search results and document presentation. Much research has been done in the field of digital libraries, but in the case of historical archives, which have particular needs, this is not the case. To this end, we investigate the use of new tools, which are based on the ontology of the historical archive in order to provide a new and effective method for document retrieval in a dynamic environment which will take into account the collaboration needs of the users.",
author = "Katifori Akrivi and Golemati Maria",
citeulike-article-id = "4149298",
keywords = "library, ontology",
posted-at = "2009-03-08 16:44:53",
priority = "2",
title = "Ontology Aided Information Retrieval in Digital Historical Archives",
url = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.6092",
year = "2007"
}
@Article{ citeulike:7057306,
abstract = {A new approach to scientometric indicators which is based on frequency distribution characteristics is presented. The pub lication productivity of ten major OECD countries during the 1981-1985 period is studied. A stochastic "cumulative ad vantage" process having a Waring-type stationary limit distri bution is assumed to underlie the publication process. This model makes it possible to estimate such indicators as the "Publication Potential" and the "Cumulative Advantage Coef ficient" which indicate the number of potential and of factual authors and the effect of the "success-breeds-success" phenom enon, respectively. A discussion of the publication behaviour of the scientific elite based on indicators of the distribution tail concludes the comparative evaluation. 10.1177/016555159001600107},
author = "T. Braun and W. Glanzel and A. Schubert",
citeulike-article-id = "7057306",
citeulike-linkout-0 = "http://dx.doi.org/10.1177/016555159001600107",
citeulike-linkout-1 = "http://jis.sagepub.com/cgi/content/abstract/16/1/37",
day = "1",
doi = "10.1177/016555159001600107",
journal = "Journal of Information Science",
keywords = "frequency\_distribution, lotka",
month = "January",
number = "1",
pages = "37--44",
posted-at = "2010-04-22 09:16:52",
priority = "2",
title = "Publication productivity: from frequency distributions to scientometric indicators",
url = "http://dx.doi.org/10.1177/016555159001600107",
volume = "16",
year = "1990"
}
@Article{ citeulike:6551067,
abstract = "This article will focus on how two different metadata harvestersOAIster and the Online Computer Library Center's (OCLC) WorldCattransform and present Dublin Core metadata extracted from CONTENTdm. It offers an examination, in plain language, of what two service providers do to metadata once they are harvested, and, in a case study, shows examples of how specific records display in both the local and aggregated interfaces. By helping metadata creators understand what happens to their metadata as it is harvested and transformed, this article aims to assist them in designing their metadata to be intelligible and useful to end-users across platforms.",
author = "Amalia Beisler and Glee Willis",
citeulike-article-id = "6551067",
citeulike-linkout-0 = "http://dx.doi.org/10.1080/19386380903095099",
doi = "10.1080/19386380903095099",
journal = "Journal of Library Metadata",
keywords = "metadata, oai",
number = "1",
pages = "65--97",
posted-at = "2010-01-16 17:08:22",
priority = "2",
publisher = "Routledge",
title = "Beyond Theory: Preparing Dublin Core Metadata for OAI-PMH Harvesting",
url = "http://dx.doi.org/10.1080/19386380903095099",
volume = "9",
year = "2009",
file = "{:references:oai\_ore:beisler.2009.jlm.oai\_pmh\_dublin\_core.pdf|}"
}
@TechReport{ citeulike:2567842,
author = "T. Berners-Lee",
citeulike-article-id = "2567842",
citeulike-linkout-0 = "http://www.w3.org/DesignIssues/Metadata",
howpublished = "http://www.w3.org/DesignIssues/Metadata",
posted-at = "2010-01-16 01:59:55",
priority = "2",
title = "Metadata Architecture",
url = "http://www.w3.org/DesignIssues/Metadata",
year = "1997"
}
@Article{ citeulike:1810860,
author = "Tim Berners-Lee and Nigel Shadbolt and Wendy Hall",
citeulike-article-id = "1810860",
citeulike-linkout-0 = "http://eprints.ecs.soton.ac.uk/12614/01/Semantic\\_Web\\_Revisted.pdf",
journal = "IEEE Intelligent Systems",
keywords = "semantic\_web",
month = "May",
pages = "96--101",
posted-at = "2010-01-16 02:06:30",
priority = "2",
title = "The Semantic Web Revisited",
url = "http://eprints.ecs.soton.ac.uk/12614/01/Semantic_Web_Revisted.pdf",
volume = "21.3",
year = "2006"
}
@Article{ citeulike:850436,
author = "P. D. Bruza and D. W. Song and K. F. Wong",
citeulike-article-id = "850436",
journal = "Journal of the American Society for Information Science",
number = "12",
pages = "1090--1105",
posted-at = "2010-01-15 16:57:19",
priority = "2",
title = "Aboutness from a Commonsense Perspective",
volume = "51",
year = "2000"
}
@InCollection{ citeulike:6071587,
abstract = "The mathematical concept of document resemblance captures well the informal notion of syntactic similarity. The resemblance can be estimated using a fixed size ” sketch” for each document. For a large collection of documents (say hundreds of millions) the size of this sketch is of the order of a few hundred bytes per document. However, for efficient large scale web indexing it is not necessary to determine the actual resemblance value: it suffices to determine whether newly encountered documents are duplicates or near-duplicates of documents already indexed. In other words, it suffices to determine whether the resemblance is above a certain threshold. In this talk we show how this determination can be made using a ” sample” of less than 50 bytes per document. The basic approach for computing resemblance has two aspects: first, resemblance is expressed as a set (of strings) intersection problem, and second, the relative size of intersections is evaluated by a process of random sampling that can be done independently for each document. The process of estimating the relative size of intersection of sets and the threshold test discussed above can be applied to arbitrary sets, and thus might be of independent interest. The algorithm for filtering near-duplicate documents discussed here has been successfully implemented and has been used for the last three years in the context of the AltaVista search engine.",
author = "Andrei Broder",
citeulike-article-id = "6071587",
citeulike-linkout-0 = "http://dx.doi.org/10.1007/3-540-45123-4\\_1",
citeulike-linkout-1 = "http://www.springerlink.com/content/ktn21yjul3r379xy",
doi = "10.1007/3-540-45123-4\_1",
journal = "Combinatorial Pattern Matching",
pages = "1--10",
posted-at = "2010-01-15 14:18:25",
priority = "2",
title = "Identifying and Filtering Near-Duplicate Documents",
url = "http://dx.doi.org/10.1007/3-540-45123-4_1",
year = "2000"
}
@Book{ citeulike:3090157,
citeulike-article-id = "3090157",
edition = "Second",
author = "Franz Baader and Diego Calvanese and Deborah L. Mcguinness and Daniele Nardi and Peter F. Patel-Schneider",
keywords = "description\_logic",
posted-at = "2009-06-30 20:36:54",
priority = "2",
publisher = "Cambridge University Press",
title = "The Description Logic Handbook",
year = "2007"
}
@InProceedings{ citeulike:1126745,
abstract = "This paper challenges some of the assumptions underlying the metadata creation process in the context of two communities of practice, based around learning object repositories and open e- Print archives. The importance of quality assurance for metadata creation is discussed and evidence from the literature, from the practical experiences of repositories and archives, and from related research and practices within other communities is presented. Issues for debate and further investigation are identified, formulated as a series of key research questions. Although there is much work to be done in the area of quality assurance for metadata creation, this paper represents an important first step towards a fuller understanding of the subject.",
author = "Jane Barton and Sarah Currier and Jessie M. N. Hey",
citeulike-article-id = "1126745",
citeulike-linkout-0 = "http://dcpapers.dublincore.org/ojs/pubs/article/view/732/728",
citeulike-linkout-1 = "http://www.siderean.com/dc2003/201\\_paper60.pdf",
keywords = "metadata\_creation, metadata\_quality",
pages = "29--36",
posted-at = "2010-01-07 13:53:50",
priority = "0",
publisher = "DCMI",
title = "Building Quality Assurance into Metadata Creation: an Analysis based on the Learning Objects and e-Prints Communities of Practice",
url = "http://dcpapers.dublincore.org/ojs/pubs/article/view/732/728",
year = "2003"
}
@Article{ citeulike:3857646,
abstract = "Findings from a data mapping and extraction exercise undertaken as part of the STAR project are described and related to recent work in the area. The exercise was undertaken in conjunction with English Heritage and encompassed five differently structured relational databases containing various results of archaeological excavations. The aim of the exercise was to demonstrate the potential benefits in cross searching data expressed as RDF and conforming to a common overarching conceptual data structure schema - the English Heritage Centre for Archaeology ontological model (CRM-EH), an extension of the CIDOC Conceptual Reference Model (CRM). A semi-automatic mapping/extraction tool proved an essential component. The viability of the approach is demonstrated by web services and a client application on an integrated data and concept network.",
author = "Ceri Binding and Keith May and Douglas Tudhope",
citeulike-article-id = "3857646",
doi = "10.1007/978-3-540-87599-4\_30",
journal = "Research and Advanced Technology for Digital Libraries",
keywords = "cidoc\_crm, semantic\_interoperability",
pages = "280--290",
posted-at = "2009-06-30 16:14:44",
priority = "2",
title = "Semantic Interoperability in Archaeological Datasets: Data Mapping and Extraction Via the CIDOC CRM",
url = "http://dx.doi.org/10.1007/978-3-540-87599-4_30",
year = "2008"
}
@Article{ citeulike:5730605,
author = "Alistair Black",
citeulike-article-id = "5730605",
citeulike-linkout-0 = "http://dx.doi.org/DOI:10.1002/aris.1440400118",
doi = "DOI:10.1002/aris.1440400118",
journal = "Annual Review of Information Science \& Technology (ARIST)",
keywords = "information\_history",
pages = "441--473",
posted-at = "2009-09-07 02:47:02",
priority = "0",
title = "Information history",
url = "http://dx.doi.org/DOI:10.1002/aris.1440400118",
volume = "40",
year = "2006",
file = "{:references:phd1st:glis702:information\_history.pdf|}"
}
@Article{ citeulike:5730696,
author = "Rayward W. Boyd",
citeulike-article-id = "5730696",
citeulike-linkout-0 = "http://dx.doi.org/doi:10.1016/0306-4573(95)00046-J",
doi = "doi:10.1016/0306-4573(95)00046-J",
issn = "0306-4573",
journal = "Information Processing and Management",
keywords = "information\_history",
number = "1",
pages = "3--17",
posted-at = "2009-09-07 03:22:17",
priority = "0",
title = "The history and historiography of information science: Some reflections",
url = "http://dx.doi.org/doi:10.1016/0306-4573(95)00046-J",
volume = "32",
year = "1996",
file = "{:references:phd1st:glis702:boyd.information.history.pdf|}"
}
@Book{ citeulike:290835,
abstract = "{Knowledge representation is at the very core of a radical idea for understanding intelligence. Instead of trying to understand or build brains from the bottom up, its goal is to understand and build intelligent behavior from the top down, putting the focus on what an agent needs to know in order to behave intelligently, how this knowledge can be represented symbolically, and how automated reasoning procedures can make this knowledge available as needed. <br><br>This landmark text takes the central concepts of knowledge representation developed over the last 50 years and illustrates them in a lucid and compelling way. Each of the various styles of representation is presented in a simple and intuitive form, and the basics of reasoning with that representation are explained in detail. This approach gives readers a solid foundation for understanding the more advanced work found in the research literature. The presentation is clear enough to be accessible to a broad audience, including researchers and practitioners in database management, information retrieval, and object-oriented systems as well as artificial intelligence. This book provides the foundation in knowledge representation and reasoning that every AI practitioner needs.<br><br>*Authors are well-recognized experts in the field who have applied the techniques to real-world problems <br>* Presents the core ideas of KR\&R in a simple straight forward approach, independent of the quirks of research systems <br>*Offers the first true synthesis of the field in over a decade}",
author = "Ronald Brachman and Hector Levesque",
citeulike-article-id = "290835",
howpublished = "Hardcover",
isbn = "1558609326",
keywords = "ai",
month = "May",
posted-at = "2009-06-30 20:42:40",
priority = "2",
publisher = "Morgan Kaufmann",
title = "Knowledge Representation and Reasoning (The Morgan Kaufmann Series in Artificial Intelligence)",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/1558609326",
year = "2004"
}
@Article{ citeulike:5024113,
abstract = "The quality of the metadata records in a digital library has a critical effect on its information access and retrieval. The open source Metadata Repository at the National Science Digital Library {(NSDL)} comprises of collections of metadata submitted from various data providers and is open for harvesting by the public. Since metadata in the repository came from many different data providers, there is a lack of consistency. This lack of consistent hampers the information services provided by the {NSDL} to its own web users as well as to aggregators who harvest the {NSDL} data. The goal of this study is to assess the quality of the current metadata records in the {NSDL} Repository. We harvested over one million Dublin Core metadata records submitted through November 2005 to the repository using the Open Archives Initiative Protocol {(OAIP).} The data harvested was loaded into an Excel database and exhaustive tabulations of all the Dublin Core metadata fields were performed. The criteria of quality assessment are based on the following areas: consistency, completeness, accuracy and local additions of data providers. This study reports on the results of the tabulations and assessment of metadata quality. Information organizations and institutions will benefit from the results of this study in determining which parts of the repository they aim to harvest. The data collected for this study will be made available to the public to contribute to promoting studies on metadata quality improvement by enabling other researchers to have access to the data for further analysis.",
author = "Yen Bui and Jung-Ran Park",
citeulike-article-id = "5024113",
keywords = "metadata, metadata\_quality",
posted-at = "2009-06-30 17:41:23",
priority = "2",
year = "2006",
pages = "1--13",
title = "An assessment of metadata quality: A case study of the National Science Digital Library Metadata Repository",
url = "http://idea.library.drexel.edu/handle/1860/1600",
file = "{:references:metadata.quality:bui.2006.nsdl\_metadata\_quality.pdf|}"
}
@Article{ citeulike:3861763,
abstract = "A study to develop a methodology for studying index consistency in machine readable cataloging (MARC) records and to study such consistency in subject cataloging practice between the Library of Congress (LC) and non-LC libraries found that consistency among indexers is difficult to achieve even when the same indexing policies and vocabulary are used.",
author = "Lois M. Chan",
citeulike-article-id = "3861763",
citeulike-linkout-0 = "http://proquest.umi.com/pqdweb?did=7096175\&\\#38;Fmt=7\&\\#38;clientId=11263\&\\#38;RQT=309\&\\#38;VName=PQD",
journal = "Information Technology and Libraries",
keywords = "interindexer\_consistency, metadata, subject\_analysis",
number = "4",
pages = "349--358",
posted-at = "2010-03-14 00:05:03",
priority = "3",
title = "Inter-Indexer Consistency in Subject Cataloging",
url = "http://proquest.umi.com/pqdweb?did=7096175&Fmt=7&clientId=11263&RQT=309&VName=PQD",
volume = "8",
year = "1989"
}
@Article{ citeulike:6588726,
abstract = "With the proliferation of Web 2.0 technologies, there is an expanded opportunity for individuals to get involved in information exchange. In this study, the sustainability of a virtual community for teachers and educators were investigated. The research model borrows the key concepts from the IS continuance model, social influence theory, the uses and gratifications paradigm, and relationship marketing to explain user intention to continue using a virtual community, as well as intention to recommend the community to others. Satisfaction, commitment, group norms are found to have significant impacts on intention to continue using and intention to recommend. Among the three factors, satisfaction has the highest impact on behavioral intentions. Individual-related factors (purposive value and self-discovery) are found to have significant impacts on user satisfaction, while social-related factors are more important in determining commitment and group norms. The results of this study provide important implications for both research and practice. 10.1177/0165551508099088",
author = "Christy M. K. Cheung and Matthew K. O. Lee",
citeulike-article-id = "6588726",
citeulike-linkout-0 = "http://dx.doi.org/10.1177/0165551508099088",
citeulike-linkout-1 = "http://jis.sagepub.com/cgi/content/abstract/35/3/279",
day = "1",
doi = "10.1177/0165551508099088",
journal = "Journal of Information Science",
month = "June",
number = "3",
pages = "279--298",
posted-at = "2010-01-25 19:07:49",
priority = "2",
title = "Understanding the sustainability of a virtual community: model development and empirical test",
url = "http://dx.doi.org/10.1177/0165551508099088",
volume = "35",
year = "2009"
}
@Article{ citeulike6581132,
abstract = "Recent proposals to improve the quality of interaction with the World Wide Web suggest considering the Web as a huge semi-structured database, so that retrieving information can be supported by the task of database querying. Under this view, it is important to represent the form of both the network, and the documents placed in the nodes of the network. However, the current proposals do not pay sufficient attention to represent document structures and reasoning about them. In this paper, we address these problems by providing a framework where Document Type Definitions (DTDs) expressed in the eXtensible Markup Language (XML) are formalized in an expressive Description Logic equipped with sound and complete inference algorithms. We provide methods for verifying conformance of a document to a DTD in polynomial time, and structural equivalence of DTDs in worst case deterministic exponential time, improving known algorithms for this problem which were double exponential. We also deal with pa...",
author = "Diego Calvanese and Giuseppe D. Giacomo and Maurizio Lenzerini",
citeulike-article-id = "6581132",
citeulike-linkout-0 = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.6641",
journal = "Journal of Logic and Computation",
keywords = "description\_logic\_approach, document\_structures",
pages = "295--318",
posted-at = "2010-01-22 21:51:43",
priority = "2",
title = "Representing and Reasoning on XML Documents: A Description Logic Approach",
url = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.6641",
volume = "9",
year = "1999"
}
@Article{ citeulike:3861772,
abstract = "It is often assumed that the amount of interindexer consistency experienced under a given method of indexing is somehow indicative of the quality of the indexing. To explore this assumption, two hypotheses are stated concerning the possible connection between interindexer consistency and indexing quality. A specific counter-example is then exhibited which shows both hypotheses to be invalid. Although a mathematical analysis of the counterexample yields certain insights, the general relationship between interindexer consistency and successful retrieval is more subtle than might have been expected. It is concluded that until equations describing this relationship have been derived, measurements of interindexer consistency will have little meaning as clues to indexing quality.",
author = "William S. Cooper",
citeulike-article-id = "3861772",
citeulike-linkout-0 = "http://dx.doi.org/10.1002/asi.4630200314",
doi = "10.1002/asi.4630200314",
journal = "American Documentation",
keywords = "interindexer\_consistency",
number = "3",
pages = "268--278",
posted-at = "2010-01-15 19:55:29",
priority = "0",
title = "Is interindexer consistency a hobgoblin?",
url = "http://dx.doi.org/10.1002/asi.4630200314",
volume = "20",
year = "1969"
}
@Book{ citeulike:111664,
abstract = "{Mining the Web: Discovering Knowledge from Hypertext Data is the first book devoted entirely to techniques for producing knowledge from the vast body of unstructured Web data. Building on an initial survey of infrastructural issuesincluding Web crawling and indexingChakrabarti examines low-level machine learning techniques as they relate specifically to the challenges of Web mining. He then devotes the final part of the book to applications that unite infrastructure and analysis to bring machine learning to bear on systematically acquired and stored data. Here the focus is on results: the strengths and weaknesses of these applications, along with their potential as foundations for further progress. From Chakrabarti's workpainstaking, critical, and forward-lookingreaders will gain the theoretical and practical understanding they need to contribute to the Web mining effort.<br><br>* A comprehensive, critical exploration of statistics-based attempts to make sense of Web Mining.<br>* Details the special challenges associated with analyzing unstructured and semi-structured data.<br>* Looks at how classical Information Retrieval techniques have been modified for use with Web data.<br>* Focuses on today's dominant learning methods: clustering and classification, hyperlink analysis, and supervised and semi-supervised learning.<br>* Analyzes current applications for resource discovery and social network analysis.<br>* An excellent way to introduce students to especially vital applications of data mining and machine learning technology.</li></ul>}",
author = "Soumen Chakrabarti",
citeulike-article-id = "111664",
howpublished = "Hardcover",
isbn = "1558607544",
keywords = "information\_retrieval",
month = "August",
posted-at = "2009-06-30 20:15:13",
priority = "2",
publisher = "{Morgan Kaufmann}",
title = "Mining the Web: Analysis of Hypertext and Semi Structured Data",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/1558607544",
year = "2002"
}
@Article{ citeulike:4867464,
author = "Lois M. Chan and Marcia L. Zeng",
citeulike-article-id = "4867464",
doi = "10.1045/june2006-chan",
journal = "D-Lib Magazine",
keywords = "interoperability, metadata",
month = "June",
number = "6",
posted-at = "2009-06-30 17:08:16",
priority = "2",
title = "{Metadata Interoperability and Standardization -- A Study of Methodology Part I Achieving Interoperability at the Schema Level}",
url = "http://dx.doi.org/10.1045/june2006-chan",
volume = "12",
year = "2006",
file = "{:references:metadata:chan.2006.dlib.metadata\_interoperability.pdf|}"
}
@Article{ citeulike:4746682,
author = "Abdus S. Chaudhry and Tan P. Jiun",
citeulike-article-id = "4746682",
issn = "0022-0418",
journal = "Journal of Documentation",
keywords = "a, archive, digital\_museum, taxonomy",
number = "6",
pages = "751--776",
posted-at = "2009-06-04 21:47:07",
priority = "3",
publisher = "Emerald Group Publishing Limited",
title = "Enhancing access to digital information resources on heritage: A case of development of a taxonomy at the Integrated Museum and Archives System in Singapore",
volume = "61",
year = "2005",
file = "{:references:archive.ontology:chaudhry\_etal\_2005.pdf|}"
}
@InCollection{ citeulike:4746665,
abstract = "This study describes the building of ontologies to enhance current digital museum archives. Ontologies are employed to move the service level from information to knowledge retrieval. This study concentrates on a design procedure that exploits Formal Concept Analysis (FCA) to obtain conceptual structures, and Description Logic (DL) to denote concept relations in logic expressions. The empirical findings reveal that development procedures help guide ontology builders to build ontological knowledge bases step by step. Furthermore, the knowledge extraction is helpful and connectable for builders and other tools.",
author = "Yu-Liang Chi",
citeulike-article-id = "4746665",
doi = "10.1007/11739685\_31",
journal = "Advances in Machine Learning and Cybernetics",
keywords = "archive, ontology",
pages = "295--304",
posted-at = "2009-06-04 21:28:54",
priority = "0",
title = "Constructing Ontologies for Sharing Knowledge in Digital Archives",
url = "http://dx.doi.org/10.1007/11739685\_31",
year = "2006",
file = "{:references:archive.ontology:chi\_2006\_lect-notes-computer-sci.pdf|}"
}
@Article{ DBLP:ChongMSL03,
author = "Quddus Chong and Anup Marwadi and Kaustubh Supekar and Yugyung Lee",
title = "Ontology Based Metadata Management in Medical Domains",
journal = "Journal of Research and Practice in Information Technology",
volume = "35",
number = "2",
year = "2003",
pages = "139--154",
bibsource = "DBLP, http://dblp.uni-trier.de",
file = "{:references:archive.ontology:chong\_etal\_2003.pdf|}"
}
@Book{ citeulike:524985,
author = "G. G. Chowdhury and Sudatta Chowdhury",
citeulike-article-id = "524985",
howpublished = "Paperback",
isbn = "1856044653",
keywords = "digital\_library",
month = "November",
posted-at = "2009-06-30 19:30:45",
priority = "2",
publisher = "Facet Publishing",
title = "Introduction to Digital Libraries",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/1856044653",
year = "2002"
}
@Article{ citeulike:1645552,
abstract = "Metadata enables users to find the resources they require, therefore it is an important component of any digital learning object repository. Much work has already been done within the learning technology community to assure metadata quality, focused on the development of metadata standards, specifications and vocabularies and their implementation within repositories. The metadata creation process has thus far been largely overlooked. There has been an assumption that metadata creation will be straightforward and that where machines cannot generate metadata effectively, authors of learning materials will be the most appropriate metadata creators. However, repositories are reporting difficulties in obtaining good quality metadata from their contributors, and it is becoming apparent that the issue of metadata creation warrants attention. This paper surveys the growing body of evidence, including three UK-based case studies, scopes the issues surrounding human-generated metadata creation and identifies questions for further investigation. Collaborative creation of metadata by resource authors and metadata specialists, and the design of tools and processes, are emerging as key areas for deeper research. Research is also needed into how end users will search learning object repositories.",
author = "Sarah Currier and Jane Barton and R\ón\án O\’beirne and Ben Ryan",
citeulike-article-id = "1645552",
doi = "10.1080/0968776042000211494",
journal = "ALT-J",
keywords = "metadata, metadata\_creation, metadata\_quality",
number = "1",
pages = "5--20",
posted-at = "2009-07-01 21:01:35",
priority = "0",
publisher = "Routledge",
title = "Quality assurance for digital learning object repositories: issues for the metadata creation process",
url = "http://dx.doi.org/10.1080/0968776042000211494",
volume = "12",
year = "2004",
file = "{:references:metadata.quality:quality-assurance-lom.pdf|}"
}
@InCollection{ citeulike:6255343,
abstract = "Even though the Dublin Core Metadata Element Set is well accepted as a general solution, it fails to describe more complex information assets and their cross-correlation. These include data from political history, history of arts and sciences, archaeology or observational data from natural history or geosciences. Therefore IFLA and ICOM are merging their core ontologies, an important step towards semantic interoperability of metadata schemata across all archives, libraries and museums. It opens new prospects for advanced global information integration services. The first draft of the combined model was published in June 2006.",
author = "Martin Doerr and Patrick LeBoeuf",
citeulike-article-id = "6255343",
citeulike-linkout-0 = "http://dx.doi.org/10.1007/978-3-540-77088-6\\_11",
doi = "10.1007/978-3-540-77088-6\_11",
journal = "Digital Libraries: Research and Development",
keywords = "cidoc, frbr",
pages = "114--123",
posted-at = "2010-01-16 02:09:02",
priority = "2",
title = "Modelling Intellectual Processes: The FRBR - CRM Harmonization",
url = "http://dx.doi.org/10.1007/978-3-540-77088-6_11",
year = "2007"
}
@InProceedings{ citeulike:6549002,
abstract = "From an architectural perspective, there is no essential distinction between data and metadata. Both can be represented in distributed active relationships {(DARs),} which are an extension of the Warwick framework {(C.} Lagoze et al., 1996). The {DAR} model is a powerful way to express relationships between networked resources and to allow such relationships to be dynamically downloadable and executable",
author = "R. Daniel and C. Lagoze and S. D. Payette",
booktitle = "Research and Technology Advances in Digital Libraries, 1998. ADL 98. Proceedings. IEEE International Forum on",
citeulike-article-id = "6549002",
citeulike-linkout-0 = "http://dx.doi.org/10.1109/ADL.1998.670428",
doi = "10.1109/ADL.1998.670428",
keywords = "active, architecture, dar, data, databases, digital, distributed, downloadable, dynamically, executable, file-import-10-01-16, framework, information, libraries, metadata, networked, relationships, resource, retrieval, structures, systems, warwick",
pages = "276--288",
posted-at = "2010-01-16 01:54:34",
priority = "2",
title = "A metadata architecture for digital libraries",
url = "http://dx.doi.org/10.1109/ADL.1998.670428",
year = "1998"
}
@Article{ citeulike:6548833,
abstract = "Purpose -- To report on the University of Toronto's implementation of an institutional repository. Design/methodology/approach -- Describe decision making process. A range of qualitative research methods were used to solicit early adopter and library concerns. Findings were then used to guide implementation. Findings -- Provides the rational behind decisions made. Argues that modified qualitative research methods may be useful to new library projects. Research limitations/implications -- The report is specific to an institution. Practical implications -- Prioritizing actions, focusing on faculty and leveraging resources, notably student assistants is key. Originality/value -- This paper provides practical information and a model which may be useful for others implementing repository services or other emerging technologies.",
author = "Rea Devakos",
citeulike-article-id = "6548833",
citeulike-linkout-0 = "http://dx.doi.org/10.1108/07378830610669556",
citeulike-linkout-1 = "http://www.emeraldinsight.com/10.1108/07378830610669556",
doi = "10.1108/07378830610669556",
journal = "Library Hi Tech",
keywords = "academic, digital, file-import-10-01-16, libraries, qualitative, research",
number = "2",
pages = "173--182",
posted-at = "2010-01-16 01:34:41",
priority = "2",
title = "Towards user responsive institutional repositories: a case study",
url = "http://dx.doi.org/10.1108/07378830610669556",
volume = "24",
year = "2006"
}
@Article{ citeulike:4217790,
abstract = "Abstract Long-term digital preservation, the process of maintaining digital objects through time to ensure continued access, has become a crucial issue in recent years. Whilst the amount of digitised information is constantly increasing, so too is the pace of progress in information technology, resulting in obsolescence of the software and hardware required to access and view digital information. Despite many organisations recognising this threat and the resulting need for preservation action, more work is required to effectively address the issue. We present in this article a framework for the long-term digital preservation of 3-D data. This framework is based on two pertinent preservation practices, emulation and metadata which ensure that the authenticity and usability, respectively, of a preserved digital object remain intact through time. An evaluation of our framework is presented which illustrates the viability of our approach in retaining accessibility, authenticity and usability for future end users.",
author = "Julie Doyle and Herna Viktor and Eric Paquet",
citeulike-article-id = "4217790",
citeulike-linkout-0 = "http://dx.doi.org/10.1007/s00799-009-0051-7",
citeulike-linkout-1 = "http://www.springerlink.com/content/r624114872486937",
doi = "10.1007/s00799-009-0051-7",
journal = "International Journal on Digital Libraries",
keywords = "metadata, preservation",
pages = "33--47",
posted-at = "2010-01-15 17:29:13",
priority = "2",
title = "Long-term digital preservation: preserving authenticity and usability of 3-D data",
url = "http://dx.doi.org/10.1007/s00799-009-0051-7",
year = "2009"
}
@Article{ citeulike:4087393,
abstract = "This article presents the methodology that has been successfully used over the past seven years by an interdisciplinary team to create the International Committee for Documentation of the International Council of Museums (CIDOC) CONCEPTUAL REFERENCE MODEL (CRM), a high-level ontology to enable information integration for cultural heritage data and their correlation with library and archive information. The CIDOC CRM is now in the process to become an International Organization for Standardization (ISO) standard. This article justifies in detail the methodology and design by functional requirements and gives examples of its contents. The CIDOC CRM analyzes the common conceptualizations behind data and metadata structures to support data transformation, mediation, and merging. It is argued that such ontologies are property-centric, in contrast to terminological systems, and should be built with different methodologies. It is demonstrated that ontological and epistemological arguments are equally important for an effective design, in particular when dealing with knowledge from the past in any domain. It is assumed that the presented methodology and the upper level of the ontology are applicable in a far wider domain.",
address = "Menlo Park, CA, USA",
author = "Martin Doerr",
citeulike-article-id = "4087393",
issn = "0738-4602",
journal = "AI Mag.",
keywords = "cidoc, cidoc\_crm",
number = "3",
pages = "75--92",
posted-at = "2009-06-30 16:10:21",
priority = "2",
publisher = "American Association for Artificial Intelligence",
title = "The CIDOC conceptual reference module: an ontological approach to semantic interoperability of metadata",
url = "http://portal.acm.org/citation.cfm?id=958678",
volume = "24",
year = "2003",
file = "{:references:archive.ontology:doerr.2003.aimag.cidoc\_crm.pdf|}"
}
@Article{ citeulike:4149301,
abstract = "In this paper, we argue that a core ontology is one of the key building blocks necessary to enable the scalable assimilation of information from diverse sources. A complete and extensible ontology that expresses the basic concepts that are common across a variety of domains and can provide the basis for specialization into domain-specific concepts and vocabularies, is essential for well-defined mappings between domain-specific knowledge representations (i.e., metadata vocabularies) and the subsequent building of a variety of services such as cross-domain searching, browsing, data mining and knowledge extraction. This paper describes the results of a series of three workshops held in 2001 and 2002 which brought together representatives from the cultural heritage and digital library communities with the goal of harmonizing their knowledge perspectives and producing a core ontology. The knowledge perspectives of these two communities were represented by the CIDOC/CRM [31], an ontology for information exchange in the cultural heritage and museum community, and the ABC ontology [33], a model for the exchange and integration of digital library information. This paper describes the mediation process between these two different knowledge biases and the results of this mediation -- the harmonization of the ABC and CIDOC/CRM ontologies, which we believe may provide a useful basis for information integration in the wider scope of the involved communities.",
author = "Martin Doerr and Jane Hunter and Carl Lagoze",
citeulike-article-id = "4149301",
citeulike-linkout-0 = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.409",
citeulike-linkout-1 = "http://journals.tdl.org/jodi/article/download/92/91",
journal = "Journal of Digital Information",
keywords = "cidoc\_crm, ontology",
number = "1",
posted-at = "2009-06-30 16:12:43",
priority = "2",
title = "Towards a core ontology for information integration",
url = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.409",
volume = "4",
year = "2003"
}
@Article{ citeulike:1003673,
author = "Stephen Downes",
citeulike-article-id = "1003673",
citeulike-linkout-0 = "http://www-jime.open.ac.uk/2004/5/downes-2004-5-disc-t.html",
journal = "Journal of Interactive Media in Education",
keywords = "metadata",
number = "5",
posted-at = "2009-12-02 00:29:53",
priority = "0",
title = "Resource Profiles",
url = "http://www-jime.open.ac.uk/2004/5/downes-2004-5-disc-t.html",
year = "2004",
file = "{:references:metadata:downes.2004.resource.profiles.pdf|}"
}
@Article{ unpublished:elenatorou,
author = "Torou Akrivi Katifori Elena and Vassilakis Costas",
keywords = "digital\_museum, information\_visualization, ontology",
posted-at = "2009-06-04 21:08:17",
priority = "3",
title = "Creating an Historical Archive Ontology: Guidelines and Evalation",
url = "http://oceanis.mm.di.uoa.gr/pened/papers/7-onto-meth.pdf",
year = "2006",
file = "{:references:archive.ontology:torou\_etal\_2006.pdf|}"
}
@Article{ citeulike:4052921,
abstract = "The digital age has caused the paradigm to shift in academic libraries both in terms of their collections and the roles of their personnel. As academic libraries begin to digitize objects in their collections, how and who in the library creates access to these resources has become a hot issue. At the University of Nebraska-Lincoln Libraries (UNL Libraries), taskforces were formed to study metadata schemes used at UNL Libraries. The taskforces identified the various metadata schemes in use and the role of various departments within UNL Libraries in the creation of metadata. They made recommendations about how to document decisions relating to metadata and how to coordinate metadata creation and digitization projects. As a result, the authors decided to survey American Research Libraries (ARL) and other peer libraries to determine their metadata workflow. This paper discusses the results of the survey and provides insight as to how libraries may meet the challenge of creating metadata through the reorganization of departments and staffing responsibilities.",
author = "Adonna Fleming and Margaret Mering and Judith A. Wolfe",
citeulike-article-id = "4052921",
doi = "10.1080/07317130802127983",
journal = "Technical Services Quarterly",
keywords = "metadata, metadata\_creation",
number = "4",
pages = "1--15",
posted-at = "2009-07-01 20:54:57",
priority = "2",
publisher = "Routledge",
title = "Library Personnel's Role in the Creation of Metadata: A Survey of Academic Libraries",
url = "http://dx.doi.org/10.1080/07317130802127983",
volume = "25",
year = "2008"
}
@Article{ citeulike:1658742,
address = "Tarrytown, NY, USA",
author = "Muriel Foulonneau",
citeulike-article-id = "1658742",
doi = "10.1016/j.ipm.2006.06.004",
issn = "0306-4573",
journal = "Inf. Process. Manage.",
keywords = "metadata, redundancy",
month = "May",
number = "3",
pages = "740--751",
posted-at = "2009-06-30 06:04:55",
priority = "2",
publisher = "Pergamon Press, Inc.",
title = "Information redundancy across metadata collections",
url = "http://dx.doi.org/10.1016/j.ipm.2006.06.004",
volume = "43",
year = "2007",
file = "{:references:metadata.use:information.redundancy.metadata.pdf|}"
}
@Book{ citeulike:622433,
abstract = {As the World Wide Web continues to expand, it becomes increasingly difficult for users to obtain information efficiently. Because most search engines read format languages such as HTML or SGML, search results reflect formatting tags more than actual page content, which is expressed in natural language. <i>Spinning the Semantic Web</i> describes an exciting new type of hierarchy and standardization that will replace the current "web of links" with a "web of meaning." Using a flexible set of languages and tools, the Semantic Web will make all available information -- display elements, metadata, services, images, and especially content -- accessible. The result will be an immense repository of information accessible for a wide range of new applications.<br /> <br /> This first handbook for the Semantic Web covers, among other topics, software agents that can negotiate and collect information, markup languages that can tag many more types of information in a document, and knowledge systems that enable machines to read Web pages and determine their reliability. The truly interdisciplinary Semantic Web combines aspects of artificial intelligence, markup languages, natural language processing, information retrieval, knowledge representation, intelligent agents, and databases.},
author = "Dieter Fensel and James A. Hendler and Henry Lieberman and Wolfgang Wahlster",
citeulike-article-id = "622433",
howpublished = "Paperback",
isbn = "026256212X",
keywords = "semantic\_web",
month = "March",
posted-at = "2009-06-30 20:24:32",
priority = "2",
publisher = "The MIT Press",
title = "Spinning the Semantic Web : Bringing the World Wide Web to Its Full Potential",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/026256212X",
year = "2005"
}
@Article{ 984325,
author = "Marcos Andr{\'e} Gon\c{c}alves and Edward A. Fox and Layne T. Watson and Neill A. Kipp",
title = "Streams, structures, spaces, scenarios, societies (5s): A formal model for digital libraries",
journal = "ACM Trans. Inf. Syst.",
volume = "22",
number = "2",
year = "2004",
issn = "1046-8188",
pages = "270--312",
doi = "http://doi.acm.org/10.1145/984321.984325",
publisher = "ACM",
address = "New York, NY, USA"
}
@Article{ citeulike:2793160,
abstract = "Abstract\ \ Digital libraries (DLs) have eluded definitional consensus and lack agreement on common theories and frameworks. This makes comparison of DLs extremely difficult, promotes ad-hoc development, and impedes interoperability. In this paper we propose a formal ontology for DLs that defines the fundamental concepts, relationships, and axiomatic rules that govern the DL domain, therefore providing a frame of reference for the discussion of essential concepts of DL design and construction. The ontology is an axiomatic, formal treatment of DLs, which distinguishes it from other approaches that informally define a number of architectural variants. The process of construction of the ontology was guided by 5S, a formal framework for digital libraries. To test its expressibility we have used the ontology to create a taxonomy of DL services and to reason about issues of reusability, extensibility, and composability. Some practical applications of the ontology are also described including: the definition of a digital library services taxonomy, the proposal of a modeling language for digital libraries, and the specification of quality metrics to evaluate digital libraries. We also demonstrate how to use the ontology to formally describe DL architectures and to prove some properties about them, thus helping to further validate the ontology.",
author = "Marcos Gon\c{c}alves and Edward Fox and Layne Watson",
citeulike-article-id = "2793160",
citeulike-linkout-0 = "http://dx.doi.org/10.1007/s00799-008-0033-1",
citeulike-linkout-1 = "http://www.ingentaconnect.com/content/klu/799/2008/00000008/00000002/00000033",
citeulike-linkout-2 = "http://www.springerlink.com/content/f74353ph47n55234",
day = "1",
doi = "10.1007/s00799-008-0033-1",
issn = "1432-5012",
journal = "International Journal on Digital Libraries",
month = "April",
number = "2",
pages = "91--114",
posted-at = "2010-01-15 20:20:39",
priority = "2",
publisher = "Springer",
title = "Towards a digital library theory: a formal digital library ontology",
url = "http://dx.doi.org/10.1007/s00799-008-0033-1",
volume = "8",
year = "2008"
}
@InProceedings{ citeulike:6544669,
author = "Jane Greenberg and Maria C. Pattuelli and Bijan Parsia and W. Davenport Robertson",
booktitle = "DCMI '01: Proceedings of the International Conference on Dublin Core and Metadata Applications 2001",
citeulike-article-id = "6544669",
keywords = "metadata",
pages = "38--46",
posted-at = "2010-01-15 17:22:41",
priority = "2",
publisher = "National Institute of Informatics, Tokyo, Japan",
title = "Author-generated Dublin Core Metadata for Web Resources: A Baseline Study in an Organization",
year = "2001"
}
@Book{ citeulike:587164,
abstract = "{Ontologies provide a common vocabulary of an area and define, with different levels of formality, the meaning of the terms and the relationships between them. Ontological engineering refers to the set of activities concerning the ontology development process, the ontology life cycle, the methods and methodologies for building ontologies, and the tool suites and languages that support them. During the last decade, increasing attention has been focused on ontologies. Ontologies are now widely used in knowledge engineering, artificial intelligence and computer science; in applications related to areas such as knowledge management, natural language processing, e-commerce, intelligent information integration, bio-informatics, education; and in new emerging fields like the semantic web. The book presents the major issues of ontological engineering and describes the most outstanding ontologies currently available. It covers the practical aspects of selecting and applying methodologies, languages, and tools for building ontologies. Ontological Engineering will be of great value to students and researchers, and to developers who want to integrate ontologies in their information systems. }",
author = "Asuncion Gomez-Perez and Oscar Corcho and Mariano Fernandez-Lopez",
citeulike-article-id = "587164",
howpublished = "Hardcover",
isbn = "1852335513",
keywords = "ontology, semantic\_web",
month = "July",
posted-at = "2009-06-30 19:52:40",
priority = "0",
publisher = "Springer",
title = "Ontological Engineering : with examples from the areas of Knowledge Management, e-Commerce and the Semantic Web. First Edition (Advanced Information and Knowledge Processing)",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/1852335513",
year = "2004"
}
@Article{ citeulike:4783697,
abstract = "Contribution to a special issue on image access. Reports on a quantitative categorical analysis of metadata elements in the Dublin Core, VRA Core, REACH and EAD metadata schemas, all of which can be used for organizing and describing images. Found that each of the examined metadata schemas contains elements that support the discovery, use, authentication and administration of images, and that the number and proportion of elements supporting functions in these classes varies per schema. Introduces a new schema comparison methodology and explores the development of a class oriented functional metadata schema for controlling images across multiple domains. (Original abstract - amended)",
author = "Jane Greenberg",
citeulike-article-id = "4783697",
citeulike-linkout-0 = "http://dx.doi.org/10.1002/asi.1170.abs",
doi = "10.1002/asi.1170.abs",
journal = "Journal of the American Society for Information Science and Technology",
keywords = "image, metadata, metadata\_standards",
number = "11",
pages = "917--924",
posted-at = "2009-09-25 21:25:13",
priority = "0",
title = "A quantitative categorical analysis of metadata elements in image-applicable metadata schemas",
url = "http://dx.doi.org/10.1002/asi.1170.abs",
volume = "52",
year = "2001",
file = "{:references:metadata.use:greenberg.2001.quantitative.metadata.element.pdf|}"
}
@Article{ citeulike:4052132,
abstract = "This research explores the capabilities of two Dublin Core automatic metadata generation applications, Klarity and DC-dot. The top level Web page for each resource, from a sample of 29 resources obtained from National Institute of Environmental Health Sciences (NIEHS), was submitted to both generators. Results indicate that extraction processing algorithms can contribute to useful automatic metadata generation. Results also indicate that harvesting metadata from META tags created by humans can have a positive impact on automatic metadata generation. The study identifies several ways in which automatic metadata generation applications can be improved and highlights several important areas of research. The conclusion is that integrating extraction of harvesting methods will be the best approach to creating optimal metadata, and more research is needed to identify when to apply which method.",
author = "Jane Greenberg",
citeulike-article-id = "4052132",
doi = "10.1300/J141v06n04\_05",
journal = "Journal of Library Metadata",
keywords = "extraction, harvest, metadata",
number = "4",
pages = "59--82",
posted-at = "2009-06-05 14:37:11",
priority = "2",
publisher = "Routledge",
title = "Metadata Extraction and Harvesting",
url = "http://dx.doi.org/10.1300/J141v06n04\_05",
volume = "6",
year = "2004",
file = "{:references:001:greenberg04metadata.pdf|}"
}
@Article{ citeulike:4783742,
abstract = "This paper reports on the automatic metadata generation applications (AMeGA) project's metadata expert survey. Automatic metadata generation research is reviewed and the study's methods, key findings and conclusions are presented. Participants anticipate greater accuracy with automatic techniques for technical metadata (e.g., ID, language, and format metadata) compared to metadata requiring intellectual discretion (e.g., subject and description metadata). Support for implementing automatic techniques paralleled anticipated accuracy results. Metadata experts are in favour of using automatic techniques, although they are generally not in favour of eliminating human evaluation or production for the more intellectually demanding metadata. Results are incorporated into Version 1.0 of the Recommended Functionalities for automatic metadata generation applications (Appendix A).",
author = "Jane Greenberg and Kristina Spurgin and Abe Crystal",
citeulike-article-id = "4783742",
journal = "International Journal of Metadata, Semantics and Ontologies",
number = "1",
pages = "3--20",
posted-at = "2009-06-30 06:28:48",
priority = "2",
title = "Functionalities for automatic metadata generation applications: a survey of metadata experts' opinions",
volume = "1",
year = "2006",
file = "{:references:metadata.autogen:autogen01.pdf|}"
}
@Book{ citeulike:1940300,
abstract = "{<P>Interested in how an efficient search engine works? Want to know what algorithms are used to rank resulting documents in response to user requests? The authors answer these and other key information retrieval design and implementation questions.</P> <P>This book is not yet another high level text. Instead, algorithms are thoroughly described, making this book ideally suited for both computer science students and practitioners who work on search-related applications. As stated in the foreword, this book provides a current, broad, and detailed overview of the field and is the only one that does so. Examples are used throughout to illustrate the algorithms.</P> <P>The authors explain how a query is ranked against a document collection using either a single or a combination of retrieval strategies, and how an assortment of utilities are integrated into the query processing scheme to improve these rankings. Methods for building and compressing text indexes, querying and retrieving documents in multiple languages, and using parallel or distributed processing to expedite the search are likewise described. </P> <P>This edition is a major expansion of the one published in 1998. Besides updating the entire book with current techniques, it includes new sections on language models, cross-language information retrieval, peer-to-peer processing, XML search, mediators, and duplicate document detection. </P>}",
author = "David A. Grossman and Ophir Frieder",
citeulike-article-id = "1940300",
howpublished = "Paperback",
isbn = "1402030045",
keywords = "information\_retrieval",
month = "December",
posted-at = "2009-06-30 20:19:32",
priority = "2",
publisher = "Springer",
title = "Information Retrieval: Algorithms and Heuristics (The Information Retrieval Series)(2nd Edition)",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/1402030045",
year = "2004"
}
@Misc{ citeulike:3861904,
author = "Tony Gill",
citeulike-article-id = "3861904",
citeulike-linkout-0 = "http://www.firstmonday.org/issues/issue9\\_5/gill/",
howpublished = "http://www.firstmonday.org/issues/issue9\\\_5/gill/",
keywords = "cidoc",
month = "May",
posted-at = "2010-01-15 02:52:17",
priority = "0",
title = "Building semantic bridges between museums, libraries and archives",
url = "http://www.firstmonday.org/issues/issue9_5/gill/",
year = "2004",
file = "{:references:archive.ontology:gill.2004.first.monday.build\_semantic\_bridges\_cidoc\_crm.pdf|}"
}
@Article{ citeulike:1725563,
abstract = "In this article, we elaborate on the meaning of quality in digital libraries (DLs) by proposing a model that is deeply grounded in a formal framework for digital libraries: 5S (Streams, Structures, Spaces, Scenarios, and Societies). For each major DL concept in the framework we formally define a number of dimensions of quality and propose a set of numerical indicators for those quality dimensions. In particular, we consider key concepts of a minimal DL: catalog, collection, digital object, metadata specification, repository, and services. Regarding quality dimensions, we consider: accessibility, accuracy, completeness, composability, conformance, consistency, effectiveness, efficiency, extensibility, pertinence, preservability, relevance, reliability, reusability, significance, similarity, and timeliness. Regarding measurement, we consider characteristics like: response time (with regard to efficiency), cost of migration (with respect to preservability), and number of service failures (to assess reliability). For some key DL concepts, the (quality dimension, numerical indicator) pairs are illustrated through their application to a number of ” real-world” digital libraries. We also discuss connections between the proposed dimensions of DL quality and an expanded version of a workshop's consensus view of the life cycle of information in digital libraries. Such connections can be used to determine when and where quality issues can be measured, assessed, and improved -- as well as how possible quality problems can be prevented, detected, and eliminated.",
address = "Tarrytown, NY, USA",
author = "M. Goncalves and B. Moreira and E. Fox and L. Watson",
citeulike-article-id = "1725563",
citeulike-linkout-0 = "http://portal.acm.org/citation.cfm?id=1241319",
citeulike-linkout-1 = "http://dx.doi.org/10.1016/j.ipm.2006.11.010",
citeulike-linkout-2 = "http://linkinghub.elsevier.com/retrieve/pii/S030645730600197X",
doi = "10.1016/j.ipm.2006.11.010",
issn = "03064573",
journal = "Information Processing \& Management",
keywords = "assessment, digital\_library",
month = "September",
number = "5",
pages = "1416--1437",
posted-at = "2010-01-15 14:01:21",
priority = "2",
publisher = "Pergamon Press, Inc.",
title = " ” What is a good digital library?” -- A quality model for digital libraries",
url = "http://dx.doi.org/10.1016/j.ipm.2006.11.010",
volume = "43",
year = "2007"
}
@Article{ citeulike:6994468,
abstract = "In this article, an approach to personal information management is described that is based on Semantic",
author = {William I. Grosky and Farshad Fotouhi and Bodo H{\"u}semann Informationsfabrik Gmbh M{\"u}nster},
citeulike-article-id = "6994468",
citeulike-linkout-0 = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.9128",
keywords = "ontology, ontology\_construction, ontomedia",
posted-at = "2010-04-10 03:50:27",
priority = "2",
title = "Table of Contents 1 OntoMedia—Semantic Multimedia Metadata Integration and Organization",
url = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.9128"
}
@TechReport{ citeulike:1556975,
abstract = "This is a specification of a precise semantics, and corresponding complete systems of inference rules, for the Resource Description Framework (RDF) and RDF Schema (RDFS).",
citeulike-article-id = "1556975",
citeulike-linkout-0 = "http://www.w3.org/TR/rdf-mt/",
day = "10",
editor = "Patrick Hayes",
howpublished = "http://www.w3.org/TR/rdf-mt/",
institution = "W3C",
keywords = "rdf, semantic",
month = "February",
posted-at = "2010-01-15 19:43:02",
priority = "2",
publisher = "World Wide Web Consortium",
series = "W3C Recommendation",
title = "RDF Semantics",
url = "http://www.w3.org/TR/rdf-mt/",
year = "2004"
}
@Article{ citeulike:6545091,
abstract = "There has been notably little convergence between information organization and information use studies. A framework for explicating the contextual interplay of information interactions and infrastructures of information, and more specifically the interface of information work and knowledge organization systems, is proposed. The theoretical foundations of the framework are based on systems theory and ecological approach. It is suggested that the interplay of information use and information infrastructures may be conceptualized as a systemic interaction, which is driven by the simultaneous influence of human activity related warrants and infrastructural affordances and constraints. The model provides an instrument that explicates the interplay of human information use and information infrastructures. 10.1177/0165551509336705",
author = "Isto Huvila",
citeulike-article-id = "6545091",
citeulike-linkout-0 = "http://dx.doi.org/10.1177/0165551509336705",
citeulike-linkout-1 = "http://jis.sagepub.com/cgi/content/abstract/35/6/695",
day = "1",
doi = "10.1177/0165551509336705",
journal = "Journal of Information Science",
month = "December",
number = "6",
pages = "695--708",
posted-at = "2010-01-15 19:34:11",
priority = "2",
title = "Ecological framework of information interactions and information infrastructures",
url = "http://dx.doi.org/10.1177/0165551509336705",
volume = "35",
year = "2009"
}
@InProceedings{ citeulike:4109359,
abstract = {The CORES metadata schemas registry is designed to enable users to discover and navigate metadata element sets. The paper reflects on some of the experiences of implementing the registry, and examines some of the issues of promoting such services in the context of a "partially Semantic Web" where metadata applications are evolving and many have not yet adopted the RDF model.},
author = {Rachel Heery and Pete Johnston and Csaba F{\"u}l{\"o}p and Andr{\'a}s Micsik},
booktitle = "DCMI '03: Proceedings of the 2003 international conference on Dublin Core and metadata applications",
citeulike-article-id = "4109359",
isbn = "0974530301",
keywords = "cores, metadata, registry, semantic, web",
location = "Seattle, Washington",
pages = "1--8",
posted-at = "2009-06-05 14:39:45",
priority = "2",
publisher = "Dublin Core Metadata Initiative",
title = "Metadata schema registries in the partially Semantic web: the CORES experience",
url = "http://portal.acm.org/citation.cfm?id=1383296.1383299",
year = "2003"
}
@Article{ citeulike:2191587,
address = "Piscataway, NJ, USA",
author = "James Hendler",
citeulike-article-id = "2191587",
doi = "10.1109/5254.920597",
issn = "1541-1672",
journal = "IEEE Intelligent Systems",
keywords = "agent, semantic\_web",
month = "March",
number = "2",
pages = "30--37",
posted-at = "2009-06-30 15:41:58",
priority = "2",
publisher = "IEEE Educational Activities Department",
title = "Agents and the Semantic Web",
url = "http://dx.doi.org/10.1109/5254.920597",
volume = "16",
year = "2001",
file = "{:references:semantic.web:hendler.2001.ieee.is.agents.semantic.web.pdf|}"
}
@Article{ citeulike:4200246,
abstract = "The conversation about metadata quality has developed slowly in libraries, hindered by unexamined assumptions about metadata carrying over from experience in the MARC environment. In the wider world, discussions about functionality must drive discussions about how quality might be determined and ensured. Because the quality-enforcing structures present in the MARC worldmature standards, common documentation, and bibliographic utilitiesare lacking in the metadata world, metadata practitioners desiring to improve the quality of metadata used in their libraries must develop and proliferate their own processes of evaluation and transformation to support essential interoperability. In this article, the author endeavors to describe how those processes might be established and sustained to support metadata quality improvement.",
author = "Diane I. Hillmann",
citeulike-article-id = "4200246",
doi = "10.1080/01639370802183008",
journal = "Cataloging \& Classification Quarterly",
keywords = "metadata, quality",
number = "1",
pages = "65--80",
posted-at = "2009-06-05 14:34:42",
priority = "0",
publisher = "Routledge",
title = "Metadata Quality: From Evaluation to Augmentation",
url = "http://dx.doi.org/10.1080/01639370802183008",
volume = "46",
year = "2008"
}
@Book{ citeulike:687659,
author = "Diane I. Hillman and Elaine L. Westbrooks",
citeulike-article-id = "687659",
howpublished = "Paperback",
isbn = "0838908829",
keywords = "metadata",
posted-at = "2009-06-30 20:29:52",
priority = "2",
year = "2004",
publisher = "American Library Association",
title = "Metadata in Practice",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0838908829"
}
@Book{ citeulike:1217375,
author = "Baden Hughes",
citeulike-article-id = "1217375",
journal = ": Digital Libraries: International Collaboration and Cross-Fertilization",
keywords = "evaluation, metadata, metadata\_quality",
pages = "320--329",
posted-at = "2009-07-01 20:59:54",
priority = "3",
title = "Metadata Quality Evaluation: Experience from the Open Language Archives Community",
url = "http://www.springerlink.com/content/4kaxeu5p2fb2nac1 ",
year = "2004"
}
@Book{ citeulike:209816,
author = "Chris Hart",
citeulike-article-id = "209816",
citeulike-linkout-0 = "http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0761959750",
citeulike-linkout-1 = "http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/0761959750",
citeulike-linkout-2 = "http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/0761959750",
citeulike-linkout-3 = "http://www.amazon.jp/exec/obidos/ASIN/0761959750",
citeulike-linkout-4 = "http://www.amazon.co.uk/exec/obidos/ASIN/0761959750/citeulike00-21",
citeulike-linkout-5 = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/0761959750",
citeulike-linkout-6 = "http://www.worldcat.org/isbn/0761959750",
citeulike-linkout-7 = "http://books.google.com/books?vid=ISBN0761959750",
citeulike-linkout-8 = "http://www.amazon.com/gp/search?keywords=0761959750\&index=books\&linkCode=qs",
citeulike-linkout-9 = "http://www.librarything.com/isbn/0761959750",
day = "01",
howpublished = "Paperback",
isbn = "0761959750",
keywords = "literature\_review",
month = "March",
posted-at = "2009-12-22 14:24:34",
priority = "0",
publisher = "SAGE Publications",
title = "Doing a Literature Review : Releasing the Social Science Research Imagination",
url = "http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0761959750",
year = "1999",
pages = "230"
}
@Article{ citeulike:1019370,
abstract = "This article presents the semantic portal MuseumFinland for publishing heterogeneous museum collections on the Semantic Web. It is shown how museums with their semantically rich and interrelated collection content can create a large, consolidated semantic collection portal together on the web. By sharing a set of ontologies, it is possible to make collections semantically interoperable, and provide the museum visitors with intelligent content-based search and browsing services to the global collection base. The architecture underlying MuseumFinland separates generic search and browsing services from the underlying application dependent schemas and metadata by a layer of logical rules. As a result, the portal creation framework and software developed has been applied successfully to other domains as well. MuseumFinland got the Semantic Web Challence Award (second prize) in 2004.",
author = "E. Hyvonen and E. Makela and M. Salminen and A. Valo and K. Viljanen and S. Saarela and M. Junnila and S. Kettula",
booktitle = "Selcted Papers from the International Semantic Web Conference, 2004 - ISWC, 2004",
citeulike-article-id = "1019370",
citeulike-linkout-0 = "http://dx.doi.org/10.1016/j.websem.2005.05.008",
citeulike-linkout-1 = "http://linkinghub.elsevier.com/retrieve/pii/S157082680500017X",
citeulike-linkout-2 = "http://www.sciencedirect.com/science/article/B758F-4GXVGBB-1/2/31b4fa1159b5bb40335853c6c25ecd50",
doi = "10.1016/j.websem.2005.05.008",
issn = "15708268",
journal = "Web Semantics: Science, Services and Agents on the World Wide Web",
keywords = "museum, ontology, semantic\_web",
month = "October",
number = "2-3",
pages = "224--241",
posted-at = "2010-01-15 02:37:08",
priority = "0",
title = "MuseumFinland—Finnish museums on the semantic web",
url = "http://dx.doi.org/10.1016/j.websem.2005.05.008",
volume = "3",
year = "2005",
file = "{:references:ontology:hyvonen.2005.jows.museum\_finland\_semantic\_web.pdf|}"
}
@Article{ citeulike6580903,
abstract = "this paper, we want to exploit this similarity to apply reasoning techniques from description logics to semi-structured data.",
author = "V. Informatik and D. Michaeli and W. Nutt and Y. Sagiv and David Michaeli and Y. {Werner Nutt}",
citeulike-article-id = "6580903",
citeulike-linkout-0 = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.2855",
keywords = "description\_logics, logic, semi-structure",
posted-at = "2010-01-22 20:55:44",
priority = "2",
title = "Classification Rules for Semi-Structured Data",
url = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.2855",
year = "1997"
}
@Book{ citeulike:3816245,
address = "88 Post Road West, Westport, CT 06881",
author = "Sheila S. Intner and Susan I. Lazinger and Jean Weihs",
citeulike-article-id = "3816245",