opennyaiorg/en_legal_ner_sm

This model is for efficiency purposes for better accuracy refer to en_legal_ner_trf

---

Paper details

Named Entity Recognition in Indian court judgments

Indian Legal Named Entity Recognition(NER): Identifying relevant named entities in an Indian legal judgement using legal NER trained on spacy.

Scores

Type	Score
F1-Score	74.87
Precision	72.98
Recall	76.85

Feature	Description
Name	en_legal_ner_sm
Version	3.2.0
spaCy	>=3.2.2,<3.3.0
Default Pipeline	token2vec, ner
Components	token2vec, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	InLegalNER Train Data GitHub
License	MIT
Author	Aman Tiwari

Load Pretrained Model

Install the model using pip

pip install https://huggingface.co/opennyaiorg/en_legal_ner_sm/resolve/main/en_legal_ner_sm-any-py3-none-any.whl

Using pretrained NER model

# Using spacy.load().
import spacy
nlp = spacy.load("en_legal_ner_sm")
text = "Section 319 Cr.P.C. contemplates a situation where the evidence adduced by the prosecution for Respondent No.3-G. Sambiah on 20th June 1984"
doc = nlp(text)

# Print indentified entites
for ent in doc.ents:
     print(ent,ent.label_)

##OUTPUT     
#Section 319 PROVISION
#Cr.P.C. STATUTE
#G. Sambiah RESPONDENT
#20th June 1984 DATE

Label Scheme

View label scheme (14 labels for 1 components)

ENTITY	BELONGS TO
LAWYER	PREAMBLE
COURT	PREAMBLE, JUDGEMENT
JUDGE	PREAMBLE, JUDGEMENT
PETITIONER	PREAMBLE, JUDGEMENT
RESPONDENT	PREAMBLE, JUDGEMENT
CASE_NUMBER	JUDGEMENT
GPE	JUDGEMENT
DATE	JUDGEMENT
ORG	JUDGEMENT
STATUTE	JUDGEMENT
WITNESS	JUDGEMENT
PRECEDENT	JUDGEMENT
PROVISION	JUDGEMENT
OTHER_PERSON	JUDGEMENT

Author - Publication

@inproceedings{kalamkar-etal-2022-named,
    title = "Named Entity Recognition in {I}ndian court judgments",
    author = "Kalamkar, Prathamesh  and
      Agarwal, Astha  and
      Tiwari, Aman  and
      Gupta, Smita  and
      Karn, Saurabh  and
      Raghavan, Vivek",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.nllp-1.15",
    doi = "10.18653/v1/2022.nllp-1.15",
    pages = "184--193",
    abstract = "Identification of named entities from legal texts is an essential building block for developing other legal Artificial Intelligence applications. Named Entities in legal texts are slightly different and more fine-grained than commonly used named entities like Person, Organization, Location etc. In this paper, we introduce a new corpus of 46545 annotated legal named entities mapped to 14 legal entity types. The Baseline model for extracting legal named entities from judgment text is also developed.",
}