es_core_news_sm-2.1.0a7

Details: https://spacy.io/models/es#es_core_news_sm

File checksum: 635634edbb74e07e41be0c7308e7cc3735aa3c11d4796dd3a2573b74d98116cd

Spanish multi-task CNN trained on the AnCora and WikiNER corpus. Assigns context-specific token vectors, POS tags, dependency parse and named entities. Supports identification of PER, LOC, ORG and MISC entities.

Feature	Description
Name	es_core_news_sm
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	10 MB
Pipeline	tagger, parser, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	AnCora, Wikipedia
License	GPL
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	89.06
ENTS_P	89.14
ENTS_R	88.97
LAS	87.12
TAGS_ACC	96.95
TOKEN_ACC	100.00
UAS	90.22

Because the model is trained on Wikipedia, it may perform inconsistently on many genres, such as social media text. The NER accuracy refers to the "silver standard" annotations in the WikiNER corpus. Accuracy on these annotations tends to be higher than correct human annotations.

Installation

pip install spacy-nightly
spacy download es_core_news_sm

es_core_news_md-2.1.0a7

Details: https://spacy.io/models/es#es_core_news_md

File checksum: 06d827f4822d06308b2a8d66d5ac526dec521d041826405cd5ade0f4d587b656

Spanish multi-task CNN trained on the AnCora and WikiNER corpus. Assigns context-specific token vectors, POS tags, dependency parse and named entities. Supports identification of PER, LOC, ORG and MISC entities.

Feature	Description
Name	es_core_news_md
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	69 MB
Pipeline	tagger, parser, ner
Vectors	533736 keys, 20000 unique vectors (50 dimensions)
Sources	AnCora, Wikipedia
License	GPL
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	89.38
ENTS_P	89.50
ENTS_R	89.27
LAS	88.35
TAGS_ACC	97.21
TOKEN_ACC	100.00
UAS	91.17

Because the model is trained on Wikipedia, it may perform inconsistently on many genres, such as social media text. The NER accuracy refers to the "silver standard" annotations in the WikiNER corpus. Accuracy on these annotations tends to be higher than correct human annotations.

Installation

pip install spacy-nightly
spacy download es_core_news_md

en_core_web_sm-2.1.0a7

Details: https://spacy.io/models/en#en_core_web_sm

File checksum: 0b6264abb56aa6163dc431c98f625791945f225738c0906c09abfd763f655ec2

English multi-task CNN trained on OntoNotes. Assigns context-specific token vectors, POS tags, dependency parse and named entities.

Feature	Description
Name	en_core_web_sm
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	10 MB
Pipeline	tagger, parser, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	OntoNotes 5
License	MIT
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	85.51
ENTS_P	85.47
ENTS_R	85.55
LAS	89.68
TAGS_ACC	96.83
TOKEN_ACC	99.06
UAS	91.57

Installation

pip install spacy-nightly
spacy download en_core_web_sm

en_core_web_md-2.1.0a7

Details: https://spacy.io/models/en#en_core_web_md

File checksum: f54a6e6a2ff34c1adb1a2eabeb67b170933453ed878125c76813dc2e31c8cf8a

English multi-task CNN trained on OntoNotes, with GloVe vectors trained on Common Crawl. Assigns word vectors, context-specific token vectors, POS tags, dependency parse and named entities.

Feature	Description
Name	en_core_web_md
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	91 MB
Pipeline	tagger, parser, ner
Vectors	684830 keys, 20000 unique vectors (300 dimensions)
Sources	OntoNotes 5, Common Crawl
License	MIT
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	86.31
ENTS_P	86.29
ENTS_R	86.33
LAS	90.00
TAGS_ACC	96.93
TOKEN_ACC	99.06
UAS	91.81

Installation

pip install spacy-nightly
spacy download en_core_web_md

en_core_web_lg-2.1.0a7

Details: https://spacy.io/models/en#en_core_web_lg

File checksum: 10b9ad440f66acc406013d7878f5dc73791849ca126d135e0c28c6c49abeedf5

English multi-task CNN trained on OntoNotes, with GloVe vectors trained on Common Crawl. Assigns word vectors, context-specific token vectors, POS tags, dependency parse and named entities.

Feature	Description
Name	en_core_web_lg
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	788 MB
Pipeline	tagger, parser, ner
Vectors	684830 keys, 684831 unique vectors (300 dimensions)
Sources	OntoNotes 5, Common Crawl
License	MIT
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	86.59
ENTS_P	86.63
ENTS_R	86.54
LAS	90.13
TAGS_ACC	96.99
TOKEN_ACC	99.06
UAS	91.90

Installation

pip install spacy-nightly
spacy download en_core_web_lg

el_core_news_sm-2.1.0a7

Details: https://spacy.io/models/el#el_core_news_sm

File checksum: 4c321bbfb499fe5ffd31ccd57edab230c999c5a4a3f8fce8d5e14b729bfcd79c

Greek pipeline with word vectors, POS tags, dependencies and named entities. Word vectors use Facebook's FastText Common Crawl vectors, pruned to a vocabulary of 20,000 items. Words outside the most frequent were mapped to the nearest neighbouring vector within the 20,000 rows retained. Syntax (dependencies and POS tags) trained from the Universal Dependencies conversion of the Greek Dependency Treebank (v2.2). Named entity annotations were created by Giannis Daras using Prodigy, using the OntoNotes 5 annotation schema.

Feature	Description
Name	el_core_news_sm
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	10 MB
Pipeline	tagger, parser, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	Greek Dependency Treebank, Daras GSOC 2018
License	CC BY-NC 4.0
Author	Giannis Daras

Accuracy

Type	Score
ENTS_F	73.26
ENTS_P	73.42
ENTS_R	73.11
LAS	81.53
TAGS_ACC	94.47
TOKEN_ACC	100.00
UAS	85.12

Installation

pip install spacy-nightly
spacy download el_core_news_sm

el_core_news_md-2.1.0a7

Details: https://spacy.io/models/el#el_core_news_md

File checksum: df30f3bb24e7e38d7aa473cf4bebada78c8eb358dfb65f98bea46fed2fe35c0d

Greek pipeline with word vectors, POS tags, dependencies and named entities. Word vectors use Facebook's FastText Common Crawl vectors, pruned to a vocabulary of 20,000 items. Words outside the most frequent were mapped to the nearest neighbouring vector within the 20,000 rows retained. Syntax (dependencies and POS tags) trained from the Universal Dependencies conversion of the Greek Dependency Treebank (v2.2). Named entity annotations were created by Giannis Daras using Prodigy, using the OntoNotes 5 annotation schema.

Feature	Description
Name	el_core_news_md
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	126 MB
Pipeline	tagger, parser, ner
Vectors	1999938 keys, 20000 unique vectors (300 dimensions)
Sources	Common Crawl, Greek Dependency Treebank, Daras GSOC 2018
License	CC BY-NC 4.0
Author	Giannis Daras

Accuracy

Type	Score
ENTS_F	78.05
ENTS_P	75.59
ENTS_R	80.67
LAS	85.10
TAGS_ACC	96.66
TOKEN_ACC	100.00
UAS	88.21

Installation

pip install spacy-nightly
spacy download el_core_news_md

de_core_news_sm-2.1.0a7

Details: https://spacy.io/models/de#de_core_news_sm

File checksum: b123755ebe4b59c55afd86c074d5f37e15fd3331dca3f2d403cc544cde1d0b25

German multi-task CNN trained on the TIGER and WikiNER corpus. Assigns context-specific token vectors, POS tags, dependency parse and named entities. Supports identification of PER, LOC, ORG and MISC entities.

Feature	Description
Name	de_core_news_sm
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	10 MB
Pipeline	tagger, parser, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	TIGER Corpus, Wikipedia
License	MIT
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	83.42
ENTS_P	84.38
ENTS_R	82.48
LAS	89.52
TAGS_ACC	97.26
TOKEN_ACC	99.48
UAS	91.65

Because the model is trained on Wikipedia, it may perform inconsistently on many genres, such as social media text. The NER accuracy refers to the "silver standard" annotations in the WikiNER corpus. Accuracy on these annotations tends to be higher than correct human annotations.

Installation

pip install spacy-nightly
spacy download de_core_news_sm

de_core_news_md-2.1.0a7

Details: https://spacy.io/models/de#de_core_news_md

File checksum: 75f9b5843021e0ff6e12e280777fa6a51c51a77f68d5b75abb1e6c68d59fdb0c

German multi-task CNN trained on the TIGER and WikiNER corpus. Assigns context-specific token vectors, POS tags, dependency parse and named entities. Supports identification of PER, LOC, ORG and MISC entities.

Feature	Description
Name	de_core_news_md
Version	2.1.0a7
spaCy	>=2.1.0a4
Model size	210 MB
Pipeline	tagger, parser, ner
Vectors	276087 keys, 20000 unique vectors (300 dimensions)
Sources	TIGER Corpus, Wikipedia
License	MIT
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	83.77
ENTS_P	84.64
ENTS_R	82.93
LAS	90.36
TAGS_ACC	97.42
TOKEN_ACC	99.48
UAS	92.26

Because the model is trained on Wikipedia, it may perform inconsistently on many genres, such as social media text. The NER accuracy refers to the "silver standard" annotations in the WikiNER corpus. Accuracy on these annotations tends to be higher than correct human annotations.

Installation

pip install spacy-nightly
spacy download de_core_news_md

xx_ent_wiki_sm-2.1.0a6

Details: https://spacy.io/models/xx#xx_ent_wiki_sm

File checksum: 9445f433985304b717b72a86f544bcaef8e571ed03cd30aa8b82d1ec8127c91a

Multi-lingual CNN trained on Nothman et al. (2010) Wikipedia corpus. Assigns named entities. Supports identification of PER, LOC, ORG and MISC entities for English, German, Spanish, French, Italian, Portuguese and Russian.

Feature	Description
Name	xx_ent_wiki_sm
Version	2.1.0a6
spaCy	>=2.1.0a4
Model size	3 MB
Pipeline	ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	Wikipedia
License	MIT
Author	Explosion AI

Accuracy

Type	Score
ENTS_F	81.58
ENTS_P	82.17
ENTS_R	81.01

Because the model is trained on Wikipedia, it may perform inconsistently on many genres, such as social media text.

Installation

pip install spacy-nightly
spacy download xx_ent_wiki_sm