Extracting tree transducer rules for syntactic MT systems can be hindered by word alignment errors that violate syntactic correspondences. We propose a novel model for unsupervised word alignment which explicitly takes into account target language constituent structure, while retaining the robustness and efficiency of the HMM alignment model. Our model’s predictions improve the yield of a tree transducer extraction system, without sacrificing alignment quality. We also discuss the impact of various posteriorbased methods of reconciling bidirectional alignments. 1

Phrase-based decoding produces state-of-theart translations with no regard for syntax. We add syntax to this process with a cohesion constraint based on a dependency tree for the source sentence. The constraint allows the decoder to employ arbitrary, non-syntactic phrases, but ensures that those phrases are translated in an order that respects the source tree’s structure. In this way, we target the phrasal decoder’s weakness in order modeling, without affecting its strengths. To further increase flexibility, we incorporate cohesion as a decoder feature, creating a soft constraint. The resulting cohesive, phrase-based decoder is shown to produce translations that are preferred over non-cohesive output in both automatic and human evaluations. 1

We present the first known direct measurement of word alignment coverage on an Arabic-English parallel corpus using inversion transduction grammar constraints. While direct measurements have been reported for several European and Asian languages, to date no results have been available for Arabic or any Semitic language despite much recent activity on Arabic-English spoken language and text translation. Many recent syntax based statistical MT models operate within the domain of ITG expressiveness, often for efficiency reasons, so it has become important to determine the extent to which the ITG constraint assumption holds. Our results on Arabic provide further evidence that ITG expressiveness appears largely sufficient for core MT models.

Abstract not found

We address the modeling, parameter estimation and search challenges that arise from the introduction of reordering models that capture non-local reordering in alignment modeling. In particular, we introduce several reordering models that utilize (pairs of) function words as contexts for alignment reordering. To address the parameter estimation challenge, we propose to estimate these reordering models from a relatively small amount of manuallyaligned corpora. To address the search challenge, we devise an iterative local search algorithm that stochastically explores reordering possibilities. By capturing non-local reordering phenomena, our proposed alignment model bears a closer resemblance to stateof-the-art translation model. Empirical results show significant improvements in alignment quality as well as in translation performance over baselines in a large-scale Chinese-English translation task. 1

Abstract not found

In this paper, we extend the HMM wordto-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. 1