Abstract
This paper describes a coreference resolution system for math problem text. Case frame dictionaries and a math taxonomy are utilized for supplying domain knowledge. The system deals with various anaphoric phenomena beyond well-studied entity coreferences.- Anthology ID:
- I17-2063
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 373–377
- Language:
- URL:
- https://aclanthology.org/I17-2063
- DOI:
- Cite (ACL):
- Takumi Ito, Takuya Matsuzaki, and Satoshi Sato. 2017. Coreference Resolution on Math Problem Text in Japanese. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 373–377, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Coreference Resolution on Math Problem Text in Japanese (Ito et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/I17-2063.pdf