Learning local word reorderings for hierarchical phrase-based statistical machine translation

Zhang, Jingyi; Utiyama, Masao; Sumita, Eiichro; Zhao, Hai; Neubig, Graham; Nakamura, Satoshi

doi:10.1007/s10590-016-9178-7

Cited by 5 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Translation Task Relative BLEU Improvement (%) Zhang et al [40] Chinese-to-English 3.5* Zhang et al [40] Japanese-to-English 2.8* Wenniger and Sima'an [41] Chinese-to-English 3.1 b Wenniger and Sima'an [41] German-to-English 0.3 b Li et al [42] Chinese-to-English 1.9* Nguyen and vogel [43] Arabic-to-English 2.4 b Nguyen and vogel [43] German-to-English 3.4 b Kazemi et al [27] English-to-Farsi 3.6* Gao et al [9] Chinese-to-English 3.6 b…”

Section: Reordering Modelmentioning

confidence: 99%

Investigating the Relationship between Classification Quality and SMT Performance in Discriminative Reordering Models

Kazemi

Toral

Way

et al. 2017

Entropy

View full text Add to dashboard Cite

Abstract:Reordering is one of the most important factors affecting the quality of the output in statistical machine translation (SMT). A considerable number of approaches that proposed addressing the reordering problem are discriminative reordering models (DRM). The core component of the DRMs is a classifier which tries to predict the correct word order of the sentence. Unfortunately, the relationship between classification quality and ultimate SMT performance has not been investigated to date. Understanding this relationship will allow researchers to select the classifier that results in the best possible MT quality. It might be assumed that there is a monotonic relationship between classification quality and SMT performance, i.e., any improvement in classification performance will be monotonically reflected in overall SMT quality. In this paper, we experimentally show that this assumption does not always hold, i.e., an improvement in classification performance might actually degrade the quality of an SMT system, from the point of view of MT automatic evaluation metrics. However, we show that if the improvement in the classification performance is high enough, we can expect the SMT quality to improve as well. In addition to this, we show that there is a negative relationship between classification accuracy and SMT performance in imbalanced parallel corpora. For these types of corpora, we provide evidence that, for the evaluation of the classifier, macro-averaged metrics such as macro-averaged F-measure are better suited than accuracy, the metric commonly used to date.

show abstract

Section: Reordering Modelmentioning

confidence: 99%

Investigating the Relationship between Classification Quality and SMT Performance in Discriminative Reordering Models

Kazemi

Toral

Way

et al. 2017

Entropy

View full text Add to dashboard Cite

show abstract

“…At the phrase level, Koehn et al (2007) proposed a lexicalized MSD model for phrasal reordering; Xiong et al (2006) proposed a feature-rich model to learn phrase reordering for BTG;and Li et al (2014) proposed a neural network method to learn a BTG reordering model. At the word level, Bisazza and Federico (2016) surveyed many word reordering models learned from alignment models for SMT, and in particular there are some neural network based reordering models, such as (Zhang et al, 2016). Our work is inspired by these works in spirit, and it can be considered to be a recurrent neural network based word-level reordering model.…”

Section: Related Workmentioning

confidence: 99%

Neural Machine Translation with Supervised Attention

Liu,

Utiyama,

Finch

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

The attention mechanisim is appealing for neural machine translation, since it is able to dynamically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in aligment accuracy. In this paper, we analyze and explain this issue from the point view of reordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the supervised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.

show abstract

“…Meanwhile, there are few attempts to improve the performance of the NMT model using linguistic characteristics for several language pairs . On the other hand, Most of the recently proposed statistical machine translation (SMT) systems have attempted to improve translation performance by using linguistic features including part-of-speech (POS) tags (Ueffing and Ney, 2013), syntax (Zhang et al, 2007), semantics (Rafael and Marta, 2011), reordering information (Zang et al, 2015;Zhang et al, 2016) and so on.…”

Section: Introductionmentioning

confidence: 99%

Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue

Park¹,

Zhao²

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino-Korean words, which can be converted into corresponding Chinese characters, account for more then fifty of the entire Korean vocabulary. Motivated by this, we propose a simple linguistically motivated solution to improve the performance of Korean-to-Chinese neural machine translation model by using their common vocabulary. We adopt Chinese characters as a translation pivot by converting Sino-Korean words in Korean sentence to Chinese characters and then train machine translation model with the converted Korean sentences as source sentences. The experimental results on Korean-to-Chinese translation demonstrate that the models with the proposed method improve translation quality up to 1.5 BLEU points in comparison to the baseline models.

show abstract

Learning local word reorderings for hierarchical phrase-based statistical machine translation

Cited by 5 publications

References 15 publications

Investigating the Relationship between Classification Quality and SMT Performance in Discriminative Reordering Models

Investigating the Relationship between Classification Quality and SMT Performance in Discriminative Reordering Models

Neural Machine Translation with Supervised Attention

Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue

Contact Info

Product

Resources

About