Local phrase reordering models for statistical machine translation

Kumar, Shankar; Byrne, William

doi:10.3115/1220575.1220596

Cited by 51 publications

(37 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We first compare the cube pruning decoder to the TTM (Kumar et al, 2006), a phrase-based SMT system implemented with Weighted FiniteState Tansducers (Allauzen et al, 2007). The system implements either a monotone phrase order translation, or an MJ1 (maximum phrase jump of 1) reordering model (Kumar and Byrne, 2005). Relative to the complex movement and translation allowed by Hiero and other models, MJ1 is clearly inferior (Dreyer et al, 2007); MJ1 was developed with efficiency in mind so as to run with a minimum of search errors in translation and to be easily and exactly realized via WFSTs.…”

Section: A Study Of Hiero Search Errors In Phrase-based Translationmentioning

confidence: 99%

Rule filtering by pattern for efficient hierarchical translation

Iglesias

Gispert

Banga

et al. 2009

Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09

Self Cite

View full text Add to dashboard Cite

We describe refinements to hierarchical translation search procedures intended to reduce both search errors and memory usage through modifications to hypothesis expansion in cube pruning and reductions in the size of the rule sets used in translation. Rules are put into syntactic classes based on the number of non-terminals and the pattern, and various filtering strategies are then applied to assess the impact on translation speed and quality. Results are reported on the 2008 NIST Arabic-toEnglish evaluation task.

show abstract

Section: A Study Of Hiero Search Errors In Phrase-based Translationmentioning

confidence: 99%

Rule filtering by pattern for efficient hierarchical translation

Iglesias

Gispert

Banga

et al. 2009

Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09

Self Cite

View full text Add to dashboard Cite

show abstract

“…Analogous to speech recognition systems, translation systems relied on language models to produce more fluent translation. While early work penalized phrase movements without considering reorderings arising from vastly differing grammatical structures across language pairs like ArabicEnglish, many researchers considered lexical reordering models that attempted to learn orientation based on content Kumar and Byrne, 2005;. These approaches may suffer from the data sparseness problem since many phrase pairs occur only once (Nguyen et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the Ninth Workshop on Statistical Machine Translation

Bojar

Buck

Federmann

et al. 2014

View full text Add to dashboard Cite

The focus of our workshop was to use parallel corpora for machine translation. Recent experimentation has shown that the performance of SMT systems varies greatly with the source language. In this workshop we encouraged researchers to investigate ways to improve the performance of SMT systems for diverse languages, including morphologically more complex languages, languages with partial free word order, and low-resource languages.Prior to the workshop, in addition to soliciting relevant papers for review and possible presentation, we conducted four shared tasks: a general translation task, a medical translation task, a quality estimation task, and a task to test automatic evaluation metrics. The medical translation task was introduced this year to address the important issue of domain adaptation within SMT. The results of the shared tasks were announced at the workshop, and these proceedings also include an overview paper for the shared tasks that summarizes the results, as well as provides information about the data used and any procedures that were followed in conducting or scoring the task. In addition, there are short papers from each participating team that describe their underlying system in greater detail.Like in previous years, we have received a far larger number of submission than we could accept for presentation. This year we have received 27 full paper submissions and 49 shared task submissions. In total WMT 2014 featured 12 full paper oral presentations and 49 shared task poster presentations.The invited talk was given by Alon Lavie (Carnegie Mellon University and Safaba Translation Solutions, Inc.) entitled "Machine Translation in Academia and in the Commercial World -a Contrastive Perspective".We would like to thank the members of the Program Committee for their timely reviews. We also would like to thank the participants of the shared task and all the other volunteers who helped with the evaluations. is a ranking of the systems that participated in its shared translation tasks, produced by aggregating pairwise sentencelevel comparisons collected from human judges. Over the past few years, there have been a number of tweaks to the aggregation formula in attempts to address issues arising from the inherent ambiguity and subjectivity of the task, as well as weaknesses in the proposed models and the manner of model selection.We continue this line of work by adapting the TrueSkill TM algorithm -an online approach for modeling the relative skills of players in ongoing competitions, such as Microsoft's Xbox Live -to the human evaluation of machine translation output. Our experimental results show that TrueSkill outperforms other recently proposed models on accuracy, and also can significantly reduce the number of pairwise annotations that need to be collected by sampling non-uniformly from the space of system competitions. IntroductionThe Workshop on Statistical Machine Translation (WMT) has long been a central event in the machine translation (MT) community for the evaluation of MT output. It hosts...

show abstract

“…While lots of efforts have been made in solving long-distance reordering (Xiong et al, 2006;Zens and Ney, 2006;Kumar and Byrne, 2005), longspan n-gram matching (Charniak et al, 2003;Shen et al, 2008;Yu et al, 2014), much less attention has been concentrated on capturing translation rule dependency, which is not explicitly modeled in most translation systems (Wu et al, 2014). SMT systems typically model the translation process as a sequence of translation steps, each of which uses a translation rule.…”

Section: Introductionmentioning

confidence: 99%

Recurrent Neural Network based Rule Sequence Model for Statistical Machine Translation

Zhu

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

The inability to model long-distance dependency has been handicapping SMT for years. Specifically, the context independence assumption makes it hard to capture the dependency between translation rules. In this paper, we introduce a novel recurrent neural network based rule sequence model to incorporate arbitrary long contextual information during estimating probabilities of rule sequences. Moreover, our model frees the translation model from keeping huge and redundant grammars, resulting in more efficient training and decoding. Experimental results show that our method achieves a 0.9 point BLEU gain over the baseline, and a significant reduction in rule table size for both phrase-based and hierarchical phrase-based systems.

show abstract

Local phrase reordering models for statistical machine translation

Cited by 51 publications

References 15 publications

Rule filtering by pattern for efficient hierarchical translation

Rule filtering by pattern for efficient hierarchical translation

Proceedings of the Ninth Workshop on Statistical Machine Translation

Recurrent Neural Network based Rule Sequence Model for Statistical Machine Translation

Contact Info

Product

Resources

About