Named Entity Experiments:590372a42f1258033da8eb63fda36d6e37c96c7a commitshttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commits/590372a42f1258033da8eb63fda36d6e37c96c7a2022-08-15T17:13:35+02:00https://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/590372a42f1258033da8eb63fda36d6e37c96c7aPrevent future objectives from affecting early stopping2022-08-15T17:13:35+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/c4c8ffd37554c7418f4cc4de5bf6e65b524da805Use fine-tuning schedule to train NER models2022-08-15T15:57:58+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/04b847a2a139b16ecd91d64e9c6d7b1b41d631c6Evaluate more often with fewer samples2022-08-15T15:57:58+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/b3810c32b0273222bf4a741b4ad74515898723c0Use parallel schedule to train NER models2022-08-13T12:56:11+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/3d99edcc43b0b13046e9af6acfd6eac9cb05f0f8Separate NerModel training schedules to `recognition.schedule`2022-08-13T12:56:11+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/63d085bde44ad3fe085107e1bee50b599e5203b9Automatically select GPU in `scripts/03_train_ner_models.sh`2022-08-11T21:08:09+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/7c0a40444e5a124f24367c46c94c02f10be33ca4Add `_fair-sequential` suffix to `03_train_ner_models.py`2022-08-10T19:42:38+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/570a2e1eab0d9d423a3a782c3008700dff3d2d9dSort `03_train_ner_models.tasks` by difficulty2022-08-10T19:42:19+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/e1f176927ab3797098eb14be20276c13b0847733Add `recognition.model.FairSequentialSchedule`2022-08-10T18:06:32+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/1717b7fa56c467a7726daa0a127f87c69484fcdcApply fixes of the `adaptor` package2022-08-09T23:14:50+02:00Vit Novotnywitiko@mail.muni.cz
See:
- <<a href="https://github.com/gaussalgo/adaptor/issues/25" rel="nofollow noreferrer noopener" target="_blank">https://github.com/gaussalgo/adaptor/issues/25</a>>
- <<a href="https://github.com/gaussalgo/adaptor/pull/26" rel="nofollow noreferrer noopener" target="_blank">https://github.com/gaussalgo/adaptor/pull/26</a>>
- <<a href="https://github.com/gaussalgo/adaptor/pull/27" rel="nofollow noreferrer noopener" target="_blank">https://github.com/gaussalgo/adaptor/pull/27</a>>https://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/faea9c48895cc91ada3738878d3cc4a47296bb5eAdd `recognition.model.NerModel`2022-08-09T15:35:57+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/6332e5db8450e3cc33a9e19c3ab09596a72221a8Recreate NER datasets2022-08-03T00:34:17+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/c263094b559161a31dfa72f88f171a9a9ecc6857Add `topn` parameter to `SearchResultList.get_tagged_sentences()`2022-08-02T17:20:25+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/f3de9f8cb8d869684a5d989aefcc949344c75b18Add `search.TaggedSentence`2022-08-02T16:14:45+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/afdeacca2f7c0d806c5ac4da7f10c91409143002Fix logging message in `SearchResultList.get_sentences_and_ner_tags()`2022-08-02T10:46:14+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/c4eb79d45a615923c7ee5ac7179aee907e2aa59cFix number of `O` tags produced in `SearchResultList.get_sentences_and_ner_ta...2022-08-02T10:37:08+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/14ffbc2ad1c95fcbd7e6ab00eada36b0e119c122Fix parentheses in `SearchResultList.get_sentences_and_ner_tags()`2022-08-02T10:25:12+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/1601565337904a04e9ffc194ff241db4f87b2c1dAdd `SearchResultList.deduplicate_sentences_and_ner_tags()`2022-08-01T22:37:58+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/6878ad6526b3b7d40ff513c2177a4faeeaba8fa4Create MLM datasets2022-08-01T21:43:55+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/a6dae3fa61b172a69301c9291cb94b4c61bad254Fix regex in `Document.get_sentences()`2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/757d1890a313d01bd32e689c7e0c7e0a50045cb7Fix type error2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/aa93414fe320a8a5983f749539221588e51cdc5eFix type error2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/ac95a13f5a4fc833945b3df2c5367d228b865ba5Fix style error2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/7066d7a22d81e3b685114c68887c5f3587df0b46Add `Document.save_sentences()` and `load_sentences()`2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/52609bd6f9c9bb3b17bd520e24299134a183411fAdd `Document.get_sentences()`2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/25e2a66c6246d6767a8f6efd8a97b749e098712dAdd `SearchResultList.load_sentences_and_ner_tags()`2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/71fe5b228739296c5046d4a8ecf5bcb931d5e0f7Create NER datasets2022-08-01T21:43:41+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/b6c0d39b8e7771525314a6d2257f16f73c8d10caPrevent crossing page boundaries to non-relevant documents2022-07-29T15:46:49+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/8b6e7818d1f1e582e941154eb5d5e0799f981e42Fail softly in `Document.get_sentence()`2022-07-28T22:31:52+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/de307fef359b5efba283e1409810c27ea6f4b99eFix type errors2022-07-28T21:36:36+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/ba69bc6bedf757530401db5180b22de1e22b7f31Shuffle in `SearchResultList.save_sentences_and_ner_tags()`2022-07-28T21:25:36+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/71be4b144e656e21024d62741bd1ffedbec11041Fix type error2022-07-28T21:06:40+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/a7f6185c756251a1aa775911d91119ff799b322dFix style error2022-07-28T20:53:03+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/0ef20dea2969256acd7ce6eeb7d546364c9a75fbSupport slicing with `Iterable[Entitity]` in `SearchResultList.__getitem__()`2022-07-28T20:52:15+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/3a864e4213a3cd76a018fe455608dd1b27f6962cUse `LOGGER.debug()` in `SearchResultList.load()`2022-07-28T20:43:14+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/79fc4afafb7ce2cd16c5ec44aedfd1284d88df61Add `SearchResultList.__add__()`2022-07-28T20:39:10+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/ca2f4bf3641c5f4b1d971f85af6e252d0abed1e9Revert `9d284fe`2022-07-28T20:29:57+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/14d80a1f7820617cc37989028b540054b46b580bAdd `Document.is_relevant`2022-07-28T20:25:37+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/1251f57088cc1e5e1642ad0b589e4e00066dc557Make `SearchResultList.save_sentences_and_ner_tags()` instance method2022-07-28T20:19:38+02:00Vit Novotnywitiko@mail.muni.czhttps://gitlab.fi.muni.cz/nlp/ahisto-modules/ner-eval/-/commit/e8a9dc638cf578a4452c285a5eb10c6abf763c9bUpdate `document.Document.relevant_pages_path` in `default.ini`2022-07-28T20:09:10+02:00Vit Novotnywitiko@mail.muni.cz