Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix sentence scoring logic considering cases #167

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix sentence scoring logic considering cases #167

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dd9afb9
Fix sentence scoring logic considering cases
min9079 Apr 15, 2014
f703023
Fix entity choosing logic to include last NN word in the sentence.
min9079 Apr 16, 2014
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 26 additions & 17 deletions ipynb/Chapter 5 - Mining Web Pages.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,7 @@
" if score > max_cluster_score:\n",
" max_cluster_score = score\n",
"\n",
" scores.append((sentence_idx, score))\n",
" scores.append((sentence_idx, max_cluster_score))\n",
"\n",
" return scores\n",
"\n",
Expand Down Expand Up @@ -569,22 +569,26 @@
" pos_tagged_tokens = [token for sent in pos_tagged_tokens for token in sent]\n",
"\n",
" all_entity_chunks = []\n",
" previous_pos = None\n",
" current_status = 'None-NN'\n",
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I apologize for taking so long to merge in this change. I'm just not totally sure where you're going with this second part of the diff where you are materializing current_status. Can you explain what's going on here?

" current_entity_chunk = []\n",
" for (token, pos) in pos_tagged_tokens:\n",
"\n",
" if pos == previous_pos and pos.startswith('NN'):\n",
" current_entity_chunk.append(token)\n",
" elif pos.startswith('NN'):\n",
" if current_entity_chunk != []:\n",
"\n",
" if pos.startswith('NN'):\n",
" if current_status == 'None-NN':\n",
" current_status = 'NN'\n",
" current_entity_chunk = [token]\n",
" else:\n",
" current_entity_chunk.append(token)\n",
" else:\n",
" if current_status == 'None-NN':\n",
" pass\n",
" else:\n",
" current_status = 'None-NN'\n",
" \n",
" # Note that current_entity_chunk could be a duplicate when appended,\n",
" # so frequency analysis again becomes a consideration\n",
"\n",
" all_entity_chunks.append((' '.join(current_entity_chunk), pos))\n",
" current_entity_chunk = [token]\n",
"\n",
" previous_pos = pos\n",
"\n",
" # Store the chunks as an index for the document\n",
" # and account for frequency while we're at it...\n",
Expand Down Expand Up @@ -633,20 +637,25 @@
" for sentence in pos_tagged_tokens:\n",
"\n",
" all_entity_chunks = []\n",
" previous_pos = None\n",
" current_status = 'None-NN'\n",
" current_entity_chunk = []\n",
"\n",
" for (token, pos) in sentence:\n",
"\n",
" if pos == previous_pos and pos.startswith('NN'):\n",
" current_entity_chunk.append(token)\n",
" elif pos.startswith('NN'):\n",
" if pos.startswith('NN'):\n",
" if current_status == 'None-NN':\n",
" current_status = 'NN'\n",
" current_entity_chunk = [token]\n",
" else:\n",
" current_entity_chunk.append(token)\n",
" else:\n",
" if current_status == 'None-NN':\n",
" pass\n",
" else:\n",
" current_status = 'None-NN'\n",
" if current_entity_chunk != []:\n",
" all_entity_chunks.append((' '.join(current_entity_chunk),\n",
" pos))\n",
" current_entity_chunk = [token]\n",
"\n",
" previous_pos = pos\n",
"\n",
" if len(all_entity_chunks) > 1:\n",
" entity_interactions.append(all_entity_chunks)\n",
Expand Down