Abstract
Dependency cohesion refers to the observation that phrases dominated by disjoint dependency subtrees in the source language generally do not overlap in the target language. It has been verified to be a useful constraint for word alignment. However, previous work either treats this as a hard constraint or uses it as a feature in discriminative models, which is ineffective for large-scale tasks. In this paper, we take dependency cohesion as a soft constraint, and integrate it into a generative model for large-scale word alignment experiments. We also propose an approximate EM algorithm and a Gibbs sampling algorithm to estimate model parameters in an unsupervised manner. Experiments on large-scale Chinese-English translation tasks demonstrate that our model achieves improvements in both alignment quality and translation quality.- Anthology ID:
- Q13-1024
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 1
- Month:
- Year:
- 2013
- Address:
- Cambridge, MA
- Editors:
- Dekang Lin, Michael Collins
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 291–300
- Language:
- URL:
- https://aclanthology.org/Q13-1024
- DOI:
- 10.1162/tacl_a_00228
- Cite (ACL):
- Zhiguo Wang and Chengqing Zong. 2013. Large-scale Word Alignment Using Soft Dependency Cohesion Constraints. Transactions of the Association for Computational Linguistics, 1:291–300.
- Cite (Informal):
- Large-scale Word Alignment Using Soft Dependency Cohesion Constraints (Wang & Zong, TACL 2013)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/Q13-1024.pdf