Abstract
We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking. Our segment-level CRF can consider higher-order label dependencies compared with conventional word-level CRF. Since it is difficult to consider all possible variable length segments, our method uses segment lattice constructed from the word-level tagging model to reduce the search space. Performing experiments on NER and chunking, we demonstrate that our method outperforms conventional word-level CRF with neural networks.- Anthology ID:
- I17-2017
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 97–102
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/I17-2017/
- DOI:
- Cite (ACL):
- Motoki Sato, Hiroyuki Shindo, Ikuya Yamada, and Yuji Matsumoto. 2017. Segment-Level Neural Conditional Random Fields for Named Entity Recognition. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 97–102, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Segment-Level Neural Conditional Random Fields for Named Entity Recognition (Sato et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/I17-2017.pdf
- Data
- CoNLL 2003