Learning the Structure of Variable-Order CRFs: a finite-state perspective

Thomas Lavergne, François Yvon


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
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
433–439
URL:
https://www.aclweb.org/anthology/D17-1044
DOI:
10.18653/v1/D17-1044
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D17-1044.pdf