Leveraging multiple languages to improve statistical MT word alignments

Filali, Karim; Bilmes, Jeffrey A.

doi:10.1109/asru.2005.1566493

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kumar et al (2007) show that multiparallel corpora can be of benefit to reach better performance in phrase-based statistical machine translation (SMT). Filali and Bilmes (2005) present a multilingual SMT-based word alignment model, extending IBM models, based on HMM models and a two step alignment procedure. Since the goal of this research is to tackle word alignment directly without considering machine translation, these works are not considered here.…”

Section: Related Workmentioning

confidence: 99%

Graph Algorithms for Multiparallel Word Alignment

ImaniGooghari¹,

Sabet²,

Senel³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements of F 1 of up to 28% over the baseline bilingual word aligner in different datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Graph Algorithms for Multiparallel Word Alignment

ImaniGooghari¹,

Sabet²,

Senel³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Moreover, it has been argued that English might not always be the optimal choice of a pivot language (Paul, Yamamoto, Sumita, & Nakamura, 2009). Finally, pivoting techniques have been also used at the word-level, e.g., for translation lexicon induction between Japanese and German using English (Tanaka, Murakami, & Ishida, 2009), or for improving word alignments (Filali & Bilmes, 2005;Kumar, Och, & Macherey, 2007). Pivot languages have also been used for lexical adaptation (Crego, Max, & Yvon, 2010).…”

Section: The Egyptian Wikipedia Is One Notable Exceptionmentioning

confidence: 99%

Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages

Nakov

2012

jair

View full text Add to dashboard Cite

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source language X 1 into a resourcerich language Y given a bi-text containing a limited number of parallel sentences for X 1 -Y and a larger bi-text for X 2 -Y for some resource-rich language X 2 that is closely related to X 1 . This is achieved by taking advantage of the opportunities that vocabulary overlap and similarities between the languages X 1 and X 2 in spelling, word order, and syntax offer:(1) we improve the word alignments for the resource-poor language, (2) we further augment it with additional translation options, and (3) we take care of potential spelling differences through appropriate transliteration. The evaluation for Indonesian→English using Malay and for Spanish→English using Portuguese and pretending Spanish is resource-poor shows an absolute gain of up to 1.35 and 3.37 BLEU points, respectively, which is an improvement over the best rivaling approaches, while using much less additional data. Overall, our method cuts the amount of necessary "real" training data by a factor of 2-5.Recent developments in statistical machine translation (SMT), e.g., the availability of efficient implementations of integrated open-source toolkits like Moses (Koehn, Hoang, Birch,

show abstract

“…Some authors have studied how multilingual parallel corpora can be used to improve bitext alignment. Filali and Bilmes (2005) use (bitext) alignments to addditional languages as features in bitext alignment, while Kumar et al (2007) interpolate alignments through multiple bridge languages to produce a bitext alignment for another language pair. Since the goal of this research is not multilingual alignment, it will not be considered further here.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Word Alignment for Massively Parallel Texts

Östling¹

2014

Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, Volume 2: Short Pa

View full text Add to dashboard Cite

There has been a great amount of work done in the field of bitext alignment, but the problem of aligning words in massively parallel texts with hundreds or thousands of languages is largely unexplored. While the basic task is similar, there are also important differences in purpose, method and evaluation between the problems. In this work, I present a nonparametric Bayesian model that can be used for simultaneous word alignment in massively parallel corpora. This method is evaluated on a corpus containing 1144 translations of the New Testament.

show abstract

Leveraging multiple languages to improve statistical MT word alignments

Cited by 9 publications

References 12 publications

Graph Algorithms for Multiparallel Word Alignment

Graph Algorithms for Multiparallel Word Alignment

Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages

Bayesian Word Alignment for Massively Parallel Texts

Contact Info

Product

Resources

About