Filtered Semi-Markov CRF
Urchade Zaratiana, Nadi Tomeh, Niama El Khbir, Pierre Holat, Thierry Charnois
Abstract
Semi-Markov CRF has been proposed as an alternative to the traditional Linear Chain CRF for text segmentation tasks such as Named Entity Recognition (NER). Unlike CRF, which treats text segmentation as token-level prediction, Semi-CRF considers segments as the basic unit, making it more expressive. However, Semi-CRF suffers from two major drawbacks: (1) quadratic complexity over sequence length, as it operates on every span of the input sequence, and (2) inferior performance compared to CRF for sequence labeling tasks like NER. In this paper, we introduce Filtered Semi-Markov CRF, a variant of Semi-CRF that addresses these issues by incorporating a filtering step to eliminate irrelevant segments, reducing complexity and search space. Our approach is evaluated on several NER benchmarks, where it outperforms both CRF and Semi-CRF while being significantly faster. The implementation of our method is available on Github.- Anthology ID:
- 2023.findings-emnlp.17
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 222–235
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.17
- DOI:
- 10.18653/v1/2023.findings-emnlp.17
- Cite (ACL):
- Urchade Zaratiana, Nadi Tomeh, Niama El Khbir, Pierre Holat, and Thierry Charnois. 2023. Filtered Semi-Markov CRF. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 222–235, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Filtered Semi-Markov CRF (Zaratiana et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-emnlp.17.pdf