Abstract
The computational complexity of linear-chain Conditional Random Fields (CRFs) makes it difficult to deal with very large label sets and long range dependencies. Such situations are not rare and arise when dealing with morphologically rich languages or joint labelling tasks. We extend here recent proposals to consider variable order CRFs. Using an effective finite-state representation of variable-length dependencies, we propose new ways to perform feature selection at large scale and report experimental results where we outperform strong baselines on a tagging task.- Anthology ID:
- D17-1044
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 433–439
- Language:
- URL:
- https://aclanthology.org/D17-1044
- DOI:
- 10.18653/v1/D17-1044
- Cite (ACL):
- Thomas Lavergne and François Yvon. 2017. Learning the Structure of Variable-Order CRFs: a finite-state perspective. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 433–439, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Learning the Structure of Variable-Order CRFs: a finite-state perspective (Lavergne & Yvon, EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/D17-1044.pdf