en_core_web_lg Open-source English Language Processing Model - Optimized for CPU, Supports Complete NLP Workflow

En Core Web Lg

Developed by spacy

Large English language processing model provided by spaCy, optimized for CPU, featuring a complete natural language processing pipeline

Sequence Labeling EnglishOpen Source License:MIT #English Text Processing #High-precision NER #Dependency Parsing

Downloads 129

Release Time : 3/2/2022

Model Overview

This is a comprehensive natural language processing model for English, including part-of-speech tagging, dependency parsing, named entity recognition, and other functionalities, suitable for text analysis and information extraction tasks

Model Features

CPU Optimization

Specially optimized for CPU processing, suitable for running in environments without GPU

Comprehensive NLP Pipeline

Includes a complete set of natural language processing components, from part-of-speech tagging to named entity recognition

High-quality Word Vectors

Includes 514,157 300-dimensional word vectors, covering a wide range of vocabulary

Model Capabilities

Part-of-Speech Tagging

Dependency Parsing

Named Entity Recognition

Sentence Segmentation

Lemmatization

Use Cases

Text Analysis

News Content Analysis

Extract entity information such as person names, locations, and organization names from news texts

NER F-score reached 85.43%

Syntax Analysis

Analyze the grammatical structure and part-of-speech tagging of sentences

Part-of-speech tagging accuracy reached 97.35%

Information Extraction

Structured Data Generation

Extract structured information from unstructured text

🚀 en_core_web_lg

English pipeline optimized for CPU, suitable for token - classification tasks.

🚀 Quick Start

This English pipeline is optimized for CPU. Its components include tok2vec, tagger, parser, senter, ner, attribute_ruler, and lemmatizer. For more details, please refer to: https://spacy.io/models/en#en_core_web_lg

📚 Documentation

Model Information

Property	Details
Model Type	`en_core_web_lg`
Version	`3.7.1`
spaCy	`>=3.7.2,<3.8.0`
Default Pipeline	`tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner`
Components	`tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner`
Vectors	514157 keys, 514157 unique vectors (300 dimensions)
Sources	OntoNotes 5 (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El - Bachouti, Robert Belvin, Ann Houston) [ClearNLP Constituent - to - Dependency Conversion](https://github.com/clir/clearnlp - guidelines/blob/master/md/components/dependency_conversion.md) (Emory University) WordNet 3.0 (Princeton University) [Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https://github.com/explosion/spacy - vectors - builder) (Explosion)
License	`MIT`
Author	Explosion

Label Scheme

View label scheme (113 labels for 3 components)

Component	Labels
`tagger`	`$`, `''`, `,`, `-LRB-`, `-RRB-`, `.`, `:`, `ADD`, `AFX`, `CC`, `CD`, `DT`, `EX`, `FW`, `HYPH`, `IN`, `JJ`, `JJR`, `JJS`, `LS`, `MD`, `NFP`, `NN`, `NNP`, `NNPS`, `NNS`, `PDT`, `POS`, `PRP`, `PRP$`, `RB`, `RBR`, `RBS`, `RP`, `SYM`, `TO`, `UH`, `VB`, `VBD`, `VBG`, `VBN`, `VBP`, `VBZ`, `WDT`, `WP`, `WP$`, `WRB`, `XX`, `_SP`, ````
`parser`	`ROOT`, `acl`, `acomp`, `advcl`, `advmod`, `agent`, `amod`, `appos`, `attr`, `aux`, `auxpass`, `case`, `cc`, `ccomp`, `compound`, `conj`, `csubj`, `csubjpass`, `dative`, `dep`, `det`, `dobj`, `expl`, `intj`, `mark`, `meta`, `neg`, `nmod`, `npadvmod`, `nsubj`, `nsubjpass`, `nummod`, `oprd`, `parataxis`, `pcomp`, `pobj`, `poss`, `preconj`, `predet`, `prep`, `prt`, `punct`, `quantmod`, `relcl`, `xcomp`
`ner`	`CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART`

Model Performance

Task	Metric	Score
NER	NER Precision	0.8516398746
NER	NER Recall	0.8569711538
NER	NER F Score	0.8542971968
TAG	TAG (XPOS) Accuracy	0.9734810915
UNLABELED_DEPENDENCIES	Unlabeled Attachment Score (UAS)	0.9208198801
LABELED_DEPENDENCIES	Labeled Attachment Score (LAS)	0.9027174273
SENTS	Sentences F - Score	0.907098331

Overall Accuracy

Type	Score
`TOKEN_ACC`	99.86
`TOKEN_P`	99.57
`TOKEN_R`	99.58
`TOKEN_F`	99.57
`TAG_ACC`	97.35
`SENTS_P`	92.19
`SENTS_R`	89.27
`SENTS_F`	90.71
`DEP_UAS`	92.08
`DEP_LAS`	90.27
`ENTS_P`	85.16
`ENTS_R`	85.70
`ENTS_F`	85.43

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご