Transfer learning for named-entity recognition with neural networks
Recent approaches based on artificial neural networks (ANNs) have shown promising results for named-entity recognition (NER). In order to achieve high performances, ANNs need to be trained on a large labeled dataset. However, labels might be difficult to obtain for the dataset on which the user want...
| Главные авторы: | , , |
|---|---|
| Другие авторы: | |
| Формат: | Статья |
| Язык: | English |
| Опубликовано: |
European Language Resources Association
2020
|
| Online-ссылка: | https://hdl.handle.net/1721.1/123340 |
| _version_ | 1826188205705134080 |
|---|---|
| author | Lee, Ji Young Dernoncourt, Franck Szolovits, Peter |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Lee, Ji Young Dernoncourt, Franck Szolovits, Peter |
| author_sort | Lee, Ji Young |
| collection | MIT |
| description | Recent approaches based on artificial neural networks (ANNs) have shown promising results for named-entity recognition (NER). In order to achieve high performances, ANNs need to be trained on a large labeled dataset. However, labels might be difficult to obtain for the dataset on which the user wants to perform NER: label scarcity is particularly pronounced for patient note de-identification, which is an instance of NER. In this work, we analyze to what extent transfer learning may address this issue. In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification. |
| first_indexed | 2024-09-23T07:56:09Z |
| format | Article |
| id | mit-1721.1/123340 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T07:56:09Z |
| publishDate | 2020 |
| publisher | European Language Resources Association |
| record_format | dspace |
| spelling | mit-1721.1/1233402022-09-23T09:44:24Z Transfer learning for named-entity recognition with neural networks Lee, Ji Young Dernoncourt, Franck Szolovits, Peter Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Recent approaches based on artificial neural networks (ANNs) have shown promising results for named-entity recognition (NER). In order to achieve high performances, ANNs need to be trained on a large labeled dataset. However, labels might be difficult to obtain for the dataset on which the user wants to perform NER: label scarcity is particularly pronounced for patient note de-identification, which is an instance of NER. In this work, we analyze to what extent transfer learning may address this issue. In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification. 2020-01-07T20:30:10Z 2020-01-07T20:30:10Z 2018-05 2019-07-11T12:20:15Z Article http://purl.org/eprint/type/ConferencePaper 979-10-95546-00-9 https://hdl.handle.net/1721.1/123340 Lee, Ji Young et al. "Transfer Learning for Named-Entity Recognition with Neural Networks." LREC 2018: Eleventh International Conference on Language Resources and Evaluation, May 2018, Miyazaki, Japan, European Language Resources Association, May 2018 © 2018 LREC en http://www.lrec-conf.org/proceedings/lrec2018/index.html LREC 2018: Eleventh International Conference on Language Resources and Evaluation Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf European Language Resources Association arXiv |
| spellingShingle | Lee, Ji Young Dernoncourt, Franck Szolovits, Peter Transfer learning for named-entity recognition with neural networks |
| title | Transfer learning for named-entity recognition with neural networks |
| title_full | Transfer learning for named-entity recognition with neural networks |
| title_fullStr | Transfer learning for named-entity recognition with neural networks |
| title_full_unstemmed | Transfer learning for named-entity recognition with neural networks |
| title_short | Transfer learning for named-entity recognition with neural networks |
| title_sort | transfer learning for named entity recognition with neural networks |
| url | https://hdl.handle.net/1721.1/123340 |
| work_keys_str_mv | AT leejiyoung transferlearningfornamedentityrecognitionwithneuralnetworks AT dernoncourtfranck transferlearningfornamedentityrecognitionwithneuralnetworks AT szolovitspeter transferlearningfornamedentityrecognitionwithneuralnetworks |