Named Entity Recognition for Russian Judicial Rulings Text
The article presents the solution of named entity recognition problem for legal Russian-language texts. We studied CRF, LSTM, BERT and BiLSTM and their combinations. The models were tested with various parameters of text preprocessing and words vector representations. The best result was shown by fa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
FRUCT
2022-11-01
|
| Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| Subjects: | |
| Online Access: | https://www.fruct.org/publications/volume-32/fruct32/files/Ave.pdf |
| _version_ | 1797986931674447872 |
|---|---|
| author | Maria Averina Olga Levanova Natalia Kasatkina |
| author_facet | Maria Averina Olga Levanova Natalia Kasatkina |
| author_sort | Maria Averina |
| collection | DOAJ |
| description | The article presents the solution of named entity recognition problem for legal Russian-language texts. We studied CRF, LSTM, BERT and BiLSTM and their combinations. The models were tested with various parameters of text preprocessing and words vector representations. The best result was shown by fastext vectorization with BiLSTM and CRF model, the value F-measure is 0.86. |
| first_indexed | 2024-04-11T07:40:48Z |
| format | Article |
| id | doaj.art-835e969760484faaa5dff1ca80382107 |
| institution | Directory Open Access Journal |
| issn | 2305-7254 2343-0737 |
| language | English |
| last_indexed | 2024-04-11T07:40:48Z |
| publishDate | 2022-11-01 |
| publisher | FRUCT |
| record_format | Article |
| series | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| spelling | doaj.art-835e969760484faaa5dff1ca803821072022-12-22T04:36:35ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372022-11-01321495510.23919/FRUCT56874.2022.9953892Named Entity Recognition for Russian Judicial Rulings TextMaria Averina0Olga Levanova1Natalia Kasatkina2P.G. Demidov Yaroslavl State University, RussiaP.G. Demidov Yaroslavl State University, RussiaP.G. Demidov Yaroslavl State University, RussiaThe article presents the solution of named entity recognition problem for legal Russian-language texts. We studied CRF, LSTM, BERT and BiLSTM and their combinations. The models were tested with various parameters of text preprocessing and words vector representations. The best result was shown by fastext vectorization with BiLSTM and CRF model, the value F-measure is 0.86.https://www.fruct.org/publications/volume-32/fruct32/files/Ave.pdfnerfasttextword2vecnamed entity recognitionrussian textjudicial rulings text |
| spellingShingle | Maria Averina Olga Levanova Natalia Kasatkina Named Entity Recognition for Russian Judicial Rulings Text Proceedings of the XXth Conference of Open Innovations Association FRUCT ner fasttext word2vec named entity recognition russian text judicial rulings text |
| title | Named Entity Recognition for Russian Judicial Rulings Text |
| title_full | Named Entity Recognition for Russian Judicial Rulings Text |
| title_fullStr | Named Entity Recognition for Russian Judicial Rulings Text |
| title_full_unstemmed | Named Entity Recognition for Russian Judicial Rulings Text |
| title_short | Named Entity Recognition for Russian Judicial Rulings Text |
| title_sort | named entity recognition for russian judicial rulings text |
| topic | ner fasttext word2vec named entity recognition russian text judicial rulings text |
| url | https://www.fruct.org/publications/volume-32/fruct32/files/Ave.pdf |
| work_keys_str_mv | AT mariaaverina namedentityrecognitionforrussianjudicialrulingstext AT olgalevanova namedentityrecognitionforrussianjudicialrulingstext AT nataliakasatkina namedentityrecognitionforrussianjudicialrulingstext |