fr_core_news_lg / README.md

Adriane Boyd

Update spaCy pipeline

d996fdb over 2 years ago

13.4 kB

	---
	tags:
	- spacy
	- token-classification
	language:
	- fr
	license: lgpl-lr
	model-index:
	- name: fr_core_news_lg
	results:
	- task:
	name: NER
	type: token-classification
	metrics:
	- name: NER Precision
	type: precision
	value: 0.8411510446
	- name: NER Recall
	type: recall
	value: 0.8413194027
	- name: NER F Score
	type: f_score
	value: 0.8412352152
	- task:
	name: TAG
	type: token-classification
	metrics:
	- name: TAG (XPOS) Accuracy
	type: accuracy
	value: 0.9442383014
	- task:
	name: POS
	type: token-classification
	metrics:
	- name: POS (UPOS) Accuracy
	type: accuracy
	value: 0.9729952587
	- task:
	name: MORPH
	type: token-classification
	metrics:
	- name: Morph (UFeats) Accuracy
	type: accuracy
	value: 0.9678251005
	- task:
	name: LEMMA
	type: token-classification
	metrics:
	- name: Lemma Accuracy
	type: accuracy
	value: 0.9071105631
	- task:
	name: UNLABELED_DEPENDENCIES
	type: token-classification
	metrics:
	- name: Unlabeled Attachment Score (UAS)
	type: f_score
	value: 0.8966076184
	- task:
	name: LABELED_DEPENDENCIES
	type: token-classification
	metrics:
	- name: Labeled Attachment Score (LAS)
	type: f_score
	value: 0.8581018519
	- task:
	name: SENTS
	type: token-classification
	metrics:
	- name: Sentences F-Score
	type: f_score
	value: 0.8963855422
	---
	### Details: https://spacy.io/models/fr#fr_core_news_lg

	French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.

	\| Feature \| Description \|
	\| --- \| --- \|
	\| Name \| `fr_core_news_lg` \|
	\| Version \| `3.4.0` \|
	\| spaCy \| `>=3.4.0,<3.5.0` \|
	\| Default Pipeline \| `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` \|
	\| Components \| `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` \|
	\| Vectors \| 500000 keys, 500000 unique vectors (300 dimensions) \|
	\| Sources \| [UD French Sequoia v2.8](https://github.com/UniversalDependencies/UD_French-Sequoia) (Candito, Marie; Seddah, Djamé; Perrier, Guy; Guillaume, Bruno)<br />[WikiNER](https://figshare.com/articles/Learning_multilingual_named_entity_recognition_from_Wikipedia/5462500) (Joel Nothman, Nicky Ringland, Will Radford, Tara Murphy, James R Curran)<br />[spaCy lookups data](https://github.com/explosion/spacy-lookups-data) (Explosion)<br />[Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)](https://spacy.io) (Explosion) \|
	\| License \| `LGPL-LR` \|
	\| Author \| [Explosion](https://explosion.ai) \|

	### Label Scheme

	<details>

	<summary>View label scheme (237 labels for 3 components)</summary>

	\| Component \| Labels \|
	\| --- \| --- \|
	\| `morphologizer` \| `POS=PROPN`, `Gender=Fem\\|Number=Sing\\|POS=DET\\|PronType=Dem`, `Gender=Fem\\|Number=Sing\\|POS=NOUN`, `Number=Plur\\|POS=PRON\\|Person=1`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `POS=SCONJ`, `POS=ADP`, `Definite=Def\\|Gender=Masc\\|Number=Sing\\|POS=DET\\|PronType=Art`, `NumType=Ord\\|POS=ADJ`, `Gender=Masc\\|Number=Sing\\|POS=NOUN`, `POS=PUNCT`, `Gender=Masc\\|Number=Sing\\|POS=PROPN`, `Number=Plur\\|POS=ADJ`, `Gender=Masc\\|Number=Plur\\|POS=NOUN`, `Definite=Ind\\|Gender=Fem\\|Number=Sing\\|POS=DET\\|PronType=Art`, `Number=Sing\\|POS=ADJ`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Imp\\|VerbForm=Fin`, `POS=ADV`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=3\\|Tense=Past\\|VerbForm=Fin`, `Gender=Fem\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Definite=Def\\|Gender=Fem\\|Number=Sing\\|POS=DET\\|PronType=Art`, `Gender=Fem\\|Number=Sing\\|POS=PROPN`, `Definite=Def\\|Number=Sing\\|POS=DET\\|PronType=Art`, `NumType=Card\\|POS=NUM`, `Definite=Def\\|Number=Plur\\|POS=DET\\|PronType=Art`, `Gender=Masc\\|Number=Plur\\|POS=ADJ`, `POS=CCONJ`, `Gender=Fem\\|Number=Plur\\|POS=NOUN`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Past\\|VerbForm=Fin`, `Gender=Masc\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `Gender=Fem\\|Number=Plur\\|POS=ADJ`, `POS=ADJ`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Past\\|VerbForm=Fin`, `POS=PRON\\|PronType=Rel`, `Number=Sing\\|POS=DET\\|Poss=Yes`, `Definite=Def\\|Gender=Masc\\|Number=Sing\\|POS=ADP\\|PronType=Art`, `Definite=Def\\|Number=Plur\\|POS=ADP\\|PronType=Art`, `Definite=Ind\\|Number=Plur\\|POS=DET\\|PronType=Art`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=3\\|Tense=Past\\|VerbForm=Fin`, `Gender=Masc\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `POS=VERB\\|VerbForm=Inf`, `Gender=Fem\\|Number=Sing\\|POS=ADJ`, `Gender=Masc\\|Number=Sing\\|POS=PRON\\|Person=3`, `Number=Plur\\|POS=DET`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|Number=Sing\\|POS=ADJ`, `Gender=Masc\\|Number=Sing\\|POS=DET\\|PronType=Dem`, `POS=ADV\\|PronType=Int`, `POS=VERB\\|Tense=Pres\\|VerbForm=Part`, `Gender=Fem\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `Definite=Ind\\|Gender=Masc\\|Number=Sing\\|POS=DET\\|PronType=Art`, `Gender=Masc\\|POS=ADJ`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Fut\\|VerbForm=Fin`, `Number=Plur\\|POS=DET\\|Poss=Yes`, `POS=AUX\\|VerbForm=Inf`, `Gender=Masc\\|Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Gender=Masc\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `POS=ADV\\|Polarity=Neg`, `Definite=Ind\\|Number=Sing\\|POS=DET\\|PronType=Art`, `Gender=Fem\\|Number=Sing\\|POS=PRON\\|Person=3`, `POS=PRON\\|Person=3\\|Reflex=Yes`, `Gender=Masc\\|POS=NOUN`, `POS=AUX\\|Tense=Past\\|VerbForm=Part`, `POS=PRON\\|Person=3`, `Number=Plur\\|POS=NOUN`, `NumType=Ord\\|Number=Sing\\|POS=ADJ`, `POS=VERB\\|Tense=Past\\|VerbForm=Part`, `POS=AUX\\|Tense=Pres\\|VerbForm=Part`, `Gender=Masc\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `Number=Sing\\|POS=PRON\\|Person=3`, `Number=Sing\\|POS=NOUN`, `Gender=Masc\\|Number=Plur\\|POS=PRON\\|Person=3`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Imp\\|VerbForm=Fin`, `Gender=Fem\\|NumType=Ord\\|Number=Sing\\|POS=ADJ`, `Number=Plur\\|POS=PROPN`, `Number=Sing\\|POS=PROPN`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=3\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|Number=Plur\\|POS=PRON\\|PronType=Dem`, `Gender=Masc\\|Number=Sing\\|POS=DET`, `Gender=Fem\\|Number=Sing\\|POS=DET\\|Poss=Yes`, `Gender=Masc\\|POS=PRON`, `POS=NOUN`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Fut\\|VerbForm=Fin`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=3\\|Tense=Fut\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Number=Plur\\|POS=PRON`, `Gender=Masc\\|NumType=Ord\\|Number=Plur\\|POS=ADJ`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=3\\|Tense=Fut\\|VerbForm=Fin`, `Gender=Fem\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Number=Sing\\|POS=PRON`, `Number=Sing\\|POS=PRON\\|PronType=Dem`, `Mood=Ind\\|POS=VERB\\|VerbForm=Fin`, `Number=Plur\\|POS=DET\\|PronType=Dem`, `Gender=Masc\\|Number=Sing\\|POS=PRON\\|Person=3\\|PronType=Prs`, `Gender=Masc\\|Number=Plur\\|POS=PRON\\|Person=3\\|PronType=Prs`, `Gender=Masc\\|Number=Sing\\|POS=PRON`, `Gender=Masc\\|Number=Sing\\|POS=PRON\\|Person=3\\|PronType=Dem`, `Number=Sing\\|POS=PRON\\|Person=2\\|PronType=Prs`, `Gender=Masc\\|Number=Sing\\|POS=PRON\\|PronType=Rel`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=3\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Sub\\|Number=Sing\\|POS=AUX\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|NumType=Ord\\|Number=Sing\\|POS=ADJ`, `POS=PRON`, `POS=NUM`, `Gender=Fem\\|POS=NOUN`, `POS=SPACE`, `Gender=Fem\\|Number=Plur\\|POS=PRON`, `Number=Plur\\|POS=PRON\\|Person=3`, `Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `Number=Sing\\|POS=PRON\\|Person=1`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Sub\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Past\\|VerbForm=Fin`, `Gender=Fem\\|Number=Sing\\|POS=PRON`, `Gender=Fem\\|Number=Sing\\|POS=PRON\\|Person=3\\|PronType=Prs`, `Mood=Sub\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `POS=INTJ`, `Number=Plur\\|POS=PRON\\|Person=2`, `NumType=Card\\|POS=PRON`, `Definite=Ind\\|Gender=Fem\\|Number=Plur\\|POS=DET\\|PronType=Art`, `Gender=Fem\\|Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `NumType=Card\\|POS=NOUN`, `POS=PRON\\|PronType=Int`, `Gender=Fem\\|Number=Plur\\|POS=PRON\\|Person=3`, `Gender=Fem\\|Number=Sing\\|POS=DET`, `Mood=Cnd\\|Number=Sing\\|POS=AUX\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Fem\\|Number=Plur\\|POS=DET`, `Mood=Sub\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Definite=Ind\\|Gender=Masc\\|Number=Plur\\|POS=DET\\|PronType=Art`, `Mood=Cnd\\|Number=Sing\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|Number=Sing\\|POS=PRON\\|PronType=Dem`, `Gender=Masc\\|Number=Plur\\|POS=PROPN`, `Mood=Cnd\\|Number=Plur\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Fem\\|Number=Sing\\|POS=PRON\\|PronType=Dem`, `Number=Sing\\|POS=DET`, `Gender=Masc\\|NumType=Card\\|Number=Plur\\|POS=NOUN`, `Gender=Fem\\|Number=Plur\\|POS=PRON\\|PronType=Dem`, `Mood=Ind\\|POS=VERB\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Fem\\|POS=PRON`, `Gender=Masc\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Gender=Fem\\|Number=Sing\\|POS=PRON\\|PronType=Rel`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=1\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Cnd\\|Number=Plur\\|POS=VERB\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|Number=Sing\\|POS=AUX\\|Tense=Past\\|VerbForm=Part`, `POS=X`, `POS=SYM`, `Mood=Imp\\|Number=Plur\\|POS=VERB\\|Person=2\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=2\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|Number=Sing\\|POS=DET\\|PronType=Int`, `Gender=Fem\\|Number=Plur\\|POS=DET\\|PronType=Int`, `POS=DET`, `Gender=Masc\\|Number=Plur\\|POS=PRON`, `Mood=Sub\\|Number=Plur\\|POS=AUX\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Ind\\|POS=VERB\\|Person=3\\|VerbForm=Fin`, `Number=Sing\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Mood=Cnd\\|Number=Plur\\|POS=VERB\\|Person=2\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=2\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Fem\\|Number=Sing\\|POS=DET\\|PronType=Int`, `Gender=Masc\\|Number=Plur\\|POS=DET`, `Gender=Fem\\|Number=Plur\\|POS=PRON\\|PronType=Rel`, `Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Gender=Masc\\|Number=Plur\\|POS=PRON\\|PronType=Rel`, `POS=VERB\\|Tense=Past\\|VerbForm=Part\\|Voice=Pass`, `Gender=Fem\\|NumType=Ord\\|Number=Plur\\|POS=ADJ`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=2\\|Tense=Fut\\|VerbForm=Fin`, `Mood=Imp\\|POS=VERB\\|Tense=Pres\\|VerbForm=Fin`, `Number=Plur\\|POS=PRON\\|Person=2\\|Reflex=Yes`, `Mood=Cnd\\|Number=Sing\\|POS=VERB\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Number=Plur\\|POS=PRON\\|Person=1\\|Reflex=Yes`, `Gender=Masc\\|NumType=Card\\|Number=Sing\\|POS=NOUN`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=1\\|Tense=Fut\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=1\\|Tense=Fut\\|VerbForm=Fin`, `Number=Sing\\|POS=PRON\\|Person=1\\|Reflex=Yes`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=1\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=AUX\\|Person=1\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=1\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Sub\\|Number=Sing\\|POS=VERB\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Gender=Masc\\|POS=PROPN`, `Mood=Cnd\\|Number=Plur\\|POS=AUX\\|Person=3\\|Tense=Pres\\|VerbForm=Fin`, `Number=Plur\\|POS=PRON\\|Person=1\\|PronType=Prs`, `Mood=Sub\\|Number=Sing\\|POS=AUX\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Number=Plur\\|POS=PRON\\|Person=2\\|PronType=Prs`, `Mood=Ind\\|Number=Sing\\|POS=VERB\\|Person=1\\|Tense=Fut\\|VerbForm=Fin`, `Gender=Fem\\|Number=Plur\\|POS=PRON\\|Person=3\\|PronType=Prs`, `Number=Sing\\|POS=PRON\\|Person=1\\|PronType=Prs`, `Mood=Cnd\\|Number=Sing\\|POS=AUX\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Sub\\|Number=Plur\\|POS=AUX\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Imp\\|Number=Plur\\|POS=VERB\\|Person=1\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Sub\\|Number=Plur\\|POS=AUX\\|Person=2\\|Tense=Pres\\|VerbForm=Fin`, `Mood=Ind\\|Number=Plur\\|POS=VERB\\|Person=2\\|Tense=Imp\\|VerbForm=Fin`, `Mood=Ind\\|Number=Sing\\|POS=AUX\\|Person=2\\|Tense=Imp\\|VerbForm=Fin`, `Number=Plur\\|POS=VERB\\|Tense=Past\\|VerbForm=Part`, `Gender=Fem\\|Number=Plur\\|POS=PROPN`, `Gender=Masc\\|NumType=Card\\|POS=NUM` \|
	\| `parser` \| `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux:pass`, `aux:tense`, `case`, `cc`, `ccomp`, `conj`, `cop`, `dep`, `det`, `expl:comp`, `expl:pass`, `expl:subj`, `fixed`, `flat:foreign`, `flat:name`, `iobj`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl:agent`, `obl:arg`, `obl:mod`, `parataxis`, `punct`, `vocative`, `xcomp` \|
	\| `ner` \| `LOC`, `MISC`, `ORG`, `PER` \|

	</details>

	### Accuracy

	\| Type \| Score \|
	\| --- \| --- \|
	\| `TOKEN_ACC` \| 99.90 \|
	\| `TOKEN_P` \| 98.44 \|
	\| `TOKEN_R` \| 98.96 \|
	\| `TOKEN_F` \| 98.70 \|
	\| `POS_ACC` \| 97.30 \|
	\| `MORPH_ACC` \| 96.78 \|
	\| `MORPH_MICRO_P` \| 98.89 \|
	\| `MORPH_MICRO_R` \| 98.02 \|
	\| `MORPH_MICRO_F` \| 98.45 \|
	\| `SENTS_P` \| 89.00 \|
	\| `SENTS_R` \| 90.29 \|
	\| `SENTS_F` \| 89.64 \|
	\| `DEP_UAS` \| 89.66 \|
	\| `DEP_LAS` \| 85.81 \|
	\| `TAG_ACC` \| 94.42 \|
	\| `LEMMA_ACC` \| 90.71 \|
	\| `ENTS_P` \| 84.12 \|
	\| `ENTS_R` \| 84.13 \|
	\| `ENTS_F` \| 84.12 \|