Abstract
This paper presents a method of designing specific high-order dependency factor on the linear chain conditional random fields (CRFs) for named entity recognition (NER). Named entities tend to be separated from each other by multiple outside tokens in a text, and thus the first-order CRF, as well as the second-order CRF, may innately lose transition information between distant named entities. The proposed design uses outside label in NER as a transmission medium of precedent entity information on the CRF. Then, empirical results apparently demonstrate that it is possible to exploit long-distance label dependency in the original first-order linear chain CRF structure upon NER while reducing computational loss rather than in the second-order CRF.- Anthology ID:
- W18-2402
- Volume:
- Proceedings of the Seventh Named Entities Workshop
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- NEWS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9–13
- Language:
- URL:
- https://aclanthology.org/W18-2402
- DOI:
- 10.18653/v1/W18-2402
- Cite (ACL):
- Wangjin Lee and Jinwook Choi. 2018. Connecting Distant Entities with Induction through Conditional Random Fields for Named Entity Recognition: Precursor-Induced CRF. In Proceedings of the Seventh Named Entities Workshop, pages 9–13, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Connecting Distant Entities with Induction through Conditional Random Fields for Named Entity Recognition: Precursor-Induced CRF (Lee & Choi, NEWS 2018)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W18-2402.pdf