What types of word alignment improve statistical machine translation?

Lambert, Patrik; Petitrenaud, Simon; Ma, Yanjun; Way, Andy

doi:10.1007/s10590-012-9123-3

Cited by 9 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For SMT, high recall is more important than precision with large training data, while precision and recall are of equal importance with small training data. This finding supports previous research (Fraser and Marcu, 2007;Lambert et al, 2012). Translation unit metrics are not predictive of SMT performance.…”

Section: Discussionsupporting

confidence: 91%

Estimating Word Alignment Quality for SMT Reordering Tasks

Stymne¹,

Tiedemann²,

Nivre³

2014

Proceedings of the Ninth Workshop on Statistical Machine Translation

View full text Add to dashboard Cite

Previous studies of the effect of word alignment on translation quality in SMT generally explore link level metrics only and mostly do not show any clear connections between alignment and SMT quality. In this paper, we specifically investigate the impact of word alignment on two pre-reordering tasks in translation, using a wider range of quality indicators than previously done. Experiments on German-English translation show that reordering may require alignment models different from those used by the core translation system. Sparse alignments with high precision on the link level, for translation units, and on the subset of crossing links, like intersected HMM models, are preferred. Unlike SMT performance the desired alignment characteristics are similar for small and large training data for the pre-reordering tasks. Moreover, we confirm previous research showing that the fuzzy reordering score is a useful and cheap proxy for performance on SMT reordering tasks.

show abstract

Section: Discussionsupporting

confidence: 91%

Estimating Word Alignment Quality for SMT Reordering Tasks

Stymne¹,

Tiedemann²,

Nivre³

2014

Proceedings of the Ninth Workshop on Statistical Machine Translation

View full text Add to dashboard Cite

show abstract

“…Since previous work has suggested that training data size influences the relation between alignment and SMT quality for small and large training data (Lambert et al, 2012), we investigated this issue also for our reordering tasks. We repeated all our experiments on a small dataset, only the News Commentary data from WMT13, with 170K sentences.…”

Section: Small Training Datamentioning

confidence: 99%

“…Word alignment is a key component in all state-ofthe-art statistical machine translation (SMT) systems, and there has been some work exploring the connection between word alignment quality and translation quality Fraser and Marcu, 2007;Lambert et al, 2012). The standard way to evaluate word alignments in this context is by using metrics like alignment error rate (AER) and F-measure on the link level, and the general conclusion appears to be that translation quality benefits from alignments with high recall (rather than precision), at least for large training data.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The standard way to evaluate word alignments in this context is by using metrics like alignment error rate (AER) and F-measure on the link level, and the general conclusion appears to be that translation quality benefits from alignments with high recall (rather than precision), at least for large training data. Although many other ways of measuring alignment quality have been proposed, such as working on translation units (Ahrenberg et al, 2000;Ayan and Dorr, 2006; Søgaard and Kuhn, 2009) or using link degree and related measures (Ahrenberg, 2010), these methods have not been used to study the relation between alignment and translation quality, with the exception of Lambert et al (2012).Word alignment is also used for many other tasks besides translation, including term bank creation (Merkel and Foo, 2007), cross-lingual annotation projection for part-of-speech tagging (Yarowsky et al, 2001), semantic roles (Pado and Lapata, 2005), pronoun anaphora (Postolache et al., 2006), and cross-lingual clustering (Täckström et al, 2012). Even within SMT itself, there are tasks such as reordering that often make crucial use of word alignments.…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Evaluation of Source to Target and Target to Source Word Alignment for English to Hindi

Babhulgaonkar¹,

Sonavane²

2021

Algorithms for Intelligent Systems

View full text Add to dashboard Cite

What types of word alignment improve statistical machine translation?

Cited by 9 publications

References 20 publications

Estimating Word Alignment Quality for SMT Reordering Tasks

Estimating Word Alignment Quality for SMT Reordering Tasks

Proceedings of the Ninth Workshop on Statistical Machine Translation

Evaluation of Source to Target and Target to Source Word Alignment for English to Hindi

Contact Info

Product

Resources

About