**Joint Entity and Relation Extraction from Scientific Documents: Role of Linguistic Information and Entity Types**


HOW TO USE:
1. Download and unzip CodeFinal.zip.
2. Set the parameters (including path to various resources, TRAIN = True/False and other input options) correctly in main.py.
3. Install the appropriate Python packages.
4. Type: python3 main.py

## Notes
- To train SpERT.PL with SciBERT, download SciBERT from https://github.com/allenai/scibert 
(under "PyTorch HuggingFace Models") and set "model_path" and "tokenizer_path" in the config file to point to the SciBERT directory.
- Similarly you can use BioBERT from https://huggingface.co/dmis-lab/biobert-base-cased-v1.1
- BioBERT gives better results than SciBERT on ADE dataset.

CITATION:
If you find our paper/code useful, please cite our paper:
Santosh Tokala Yaswanth Sri Sai, Prantika Chakraborty, Sudakshina Dutta, Debarshi Kumar Sanyal and Partha Pratim Das, Joint Entity and Relation Extraction from Scientific Documents: Role of Linguistic Information and Entity Types. In 2nd Workshop on Extraction and Evaluation of Knowledge Entities from Scientific Documents (EEKE2021)
at the ACM/IEEE Joint Conference on Digital Libraries 2021 (JCDL2021), Online.


ACKNOWLEDGEMENT:
The code makes modifications to SpERT (https://github.com/lavis-nlp/spert/) to develop SpERT.PL which uses part-of-speech information and entity logits.