HMM word-to-phrase alignment with dependency constraints
Ma, Yanjun and Way, Andy (2010) HMM word-to-phrase alignment with dependency constraints. In: SSST 2010 - 4th Workshop on Syntax and Structure in Statistical Translation, 28 August 2010, Beijing, China.
Full text available as:
In this paper, we extend the HMMwordto-phrase alignment model with syntactic dependency constraints. The syntactic
dependencies between multiple words in one language are introduced into the model in a bid to produce coherent
alignments. Our experimental results on a variety of Chinese–English data show that our syntactically constrained
model can lead to as much as a 3.24% relative improvement in BLEU score over current HMM word-to-phrase alignment models on a Phrase-Based Statistical Machine Translation system when the training data is small, and a comparable performance compared to IBM model 4 on a Hiero-style system
with larger training data. An intrinsic alignment quality evaluation shows that our alignment model with dependency
constraints leads to improvements in both precision (by 1.74% relative) and recall (by 1.75% relative) over the model without dependency information.
Archive Staff Only: edit this record