Commit Graph

10191 Commits

Author SHA1 Message Date
svlandeg
ffae7d3555 sentence encoder only (removing article/mention encoder) 2019-06-18 00:05:47 +02:00
svlandeg
6332af40de baseline performances: oracle KB, random and prior prob 2019-06-17 14:39:40 +02:00
svlandeg
24db1392b9 reprocessing all of wikipedia for training data 2019-06-16 21:14:45 +02:00
svlandeg
81731907ba performance per entity type 2019-06-14 19:55:46 +02:00
svlandeg
b312f2d0e7 redo training data to be independent of KB and entity-level instead of doc-level 2019-06-14 15:55:26 +02:00
svlandeg
0b04d142de regenerating KB 2019-06-13 22:32:56 +02:00
svlandeg
78dd3e11da write entity linking pipe to file and keep vocab consistent between kb and nlp 2019-06-13 16:25:39 +02:00
svlandeg
b12001f368 small fixes 2019-06-12 22:05:53 +02:00
svlandeg
6521cfa132 speeding up training 2019-06-12 13:37:05 +02:00
svlandeg
66813a1fdc speed up predictions 2019-06-11 14:18:20 +02:00
svlandeg
fe1ed432ef eval on dev set, varying combo's of prior and context scores 2019-06-11 11:40:58 +02:00
svlandeg
83dc7b46fd first tests with EL pipe 2019-06-10 21:25:26 +02:00
svlandeg
7de1ee69b8 training loop in proper pipe format 2019-06-07 15:55:10 +02:00
svlandeg
0486ccabfd introduce goldparse.links 2019-06-07 13:54:45 +02:00
svlandeg
a5c061f506 storing NEL training data in GoldParse objects 2019-06-07 12:58:42 +02:00
svlandeg
61f0e2af65 code cleanup 2019-06-06 20:22:14 +02:00
svlandeg
d8b435ceff pretraining description vectors and storing them in the KB 2019-06-06 19:51:27 +02:00
svlandeg
5c723c32c3 entity vectors in the KB + serialization of them 2019-06-05 18:29:18 +02:00
svlandeg
9abbd0899f separate entity encoder to get 64D descriptions 2019-06-05 00:09:46 +02:00
svlandeg
fb37cdb2d3 implementing el pipe in pipes.pyx (not tested yet) 2019-06-03 21:32:54 +02:00
svlandeg
d83a1e3052 Merge branch 'master' into feature/nel-wiki 2019-06-03 09:35:10 +02:00
svlandeg
9e88763dab 60% acc run 2019-06-03 08:04:49 +02:00
Ines Montani
e703301129 Update universe [ci skip] 2019-06-02 13:55:55 +02:00
Ines Montani
892e72451f Update universe [ci skip] 2019-06-02 12:58:12 +02:00
Ines Montani
42de5be90c Tidy up universe [ci skip] 2019-06-02 12:38:48 +02:00
Nirant
638caba9b5 Add multiple packages to universe.json (#3809) [ci skip]
* Add multiple packages to universe.json

Added following packages: NLPArchitect, NLPRe, Chatterbot, alibi, NeuroNER

* Auto-format

* Update slogan (probably just copy-paste mistake)

* Adjust formatting

* Update tags / categories
2019-06-02 12:35:52 +02:00
Germán
86eb817b74 Overwrites default getter for like_num in Spanish by adding _num_words and like_num to lex_attrs.py (#3810) (closes #3803))
* (#3803) Spanish like_num returning false for number-like token

* (#3803) Spanish like_num now returning True for number-like token
2019-06-02 12:22:57 +02:00
Nirant
d4d1eab5e1 Add Baderlab/saber to universe.json (#3806) 2019-06-01 17:36:40 +02:00
Nirant
a5d92a3035 Create NirantK.md (#3807) [ci skip] 2019-06-01 17:36:06 +02:00
Ines Montani
6be7d07315
Update UNIVERSE.md 2019-06-01 16:37:06 +02:00
Ines Montani
09e78b52cf Improve E024 text for incorrect GoldParse (closes #3558) 2019-06-01 14:37:27 +02:00
Ines Montani
0c74506c9c Fix typos in docs (closes #3802) [ci skip] 2019-06-01 11:35:01 +02:00
Nipun Sadvilkar
1f13005751 Incorrect Token attribute ent_iob_ description (#3800)
* Incorrect Token attribute ent_iob_ description

* Add spaCy contributor agreement
2019-05-31 16:50:45 +02:00
Ramanan Balakrishnan
26c37c5a4d fix all references to BILUO annotation format (#3797) 2019-05-31 12:19:19 +02:00
Ines Montani
a7fd42d937 Make jsonschema dependency optional (#3784) 2019-05-30 14:34:58 +02:00
svlandeg
268a52ead7 experimenting with cosine sim for negative examples (not OK yet) 2019-05-29 16:07:53 +02:00
mak
89379a7fa4 Corrected example model URL in requirements.txt (#3786)
The URL used to show how to add a model to the requirements.txt had the old release path (excl. explosion).
2019-05-29 10:51:55 +02:00
svlandeg
a761929fa5 context encoder combining sentence and article 2019-05-28 18:14:49 +02:00
Ines Montani
a8416c46f7 Use string name in setup.py
Hopefully this will trick GitHub's parser into recognising it as a Python package and show us the dependents / "used by" statistics 🤞
2019-05-28 17:11:39 +02:00
svlandeg
992fa92b66 refactor again to clusters of entities and cosine similarity 2019-05-28 00:05:22 +02:00
svlandeg
8c4aa076bc small fixes 2019-05-27 14:29:38 +02:00
Ujwal Narayan
ed7be3f64c Update norm_exceptions.py (#3778)
* Update norm_exceptions.py

Extended the Currency set to include Franc, Indian Rupee, Bangladeshi Taka, Korean Won, Mexican Dollar, and Egyptian Pound

* Fix formatting [ci skip]
2019-05-27 11:52:52 +02:00
svlandeg
cfc27d7ff9 using Tok2Vec instead 2019-05-26 23:39:46 +02:00
svlandeg
abf9af81c9 learn rate en epochs 2019-05-24 22:04:25 +02:00
estr4ng7d
604acb6ace Marathi Language Support (#3767)
* Adding Marathi language details and folder to it

* Adding few changes and running tests

* Adding few changes and running tests

* Update __init__.py

mh -> mr

* Rename spacy/lang/mh/__init__.py to spacy/lang/mr/__init__.py

* mh -> mr
2019-05-24 14:29:42 +02:00
Ines Montani
7634812172 Document Language.evaluate 2019-05-24 14:06:36 +02:00
Ines Montani
45e6855550 Update Language.update docs 2019-05-24 14:06:26 +02:00
Ines Montani
b78a8dc1d2 Update Scorer and add API docs 2019-05-24 14:06:04 +02:00
svlandeg
86ed771e0b adding local sentence encoder 2019-05-23 16:59:11 +02:00
svlandeg
4392c01b7b obtain sentence for each mention 2019-05-23 15:37:05 +02:00