nalaf
nalaf copied to clipboard
NLP framework in python for entity recognition and relationship extraction
Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.24.3 to 1.26.5. Release notes Sourced from urllib3's releases. 1.26.5 :warning: IMPORTANT: urllib3 v2.0 will drop support for Python 2: Read more in the v2.0 Roadmap Fixed...
``` shell python example_annotate.py -c /usr/local/bin/ -s "This is c.A1003G an example" Due to a dependence on GNormPlus, running nalaf with -s and -d switches might take a long time....
Some classes in nalaf depend on directly, instead of as a parameter. PRO_CLASS_ID = 'e_1' MUT_CLASS_ID = 'e_2' ORG_CLASS_ID = 'e_3' PRO_REL_MUT_CLASS_ID = 'r_4' # e_1/e_2 PRO_REL_ORG_CLASS_ID = 'r_5' #...
- Wiki page: https://github.com/Rostlab/nalaf/wiki/Output-Formats - [ ] Confirm if you still use the simple JSON export - `if yes`: - [ ] fix documentation of format (I guess it's wrong...
- [ ] Test coverage: https://coveralls.io/
Maybe use Jython
Indeed old doc didn't have `s4s1f1p1` but its text was somehow included at the end of `s4s1p2`. By parsing the doc again in latest version of tagtog, `s4s1f1p1` is indeed...
The commit c541aab90453c38d9390dfaefb57ec0ce15a16da may have created problems with other datasets. Verify this and implement due unit tests. **Bug Indeed** --> genormplus-generated documents so far create the parts with names "title"...
- [ ] Rename relations_context and move to nalaf - [ ] Rename relations_entityhead and move to nalaf - [ ] Move all relna feature files to nalaf and rename...