Cyril Goutte, Nicola Cancedda, Marc Dymetman, and George Foster (eds)
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- book
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.001.0001
- Subject:
- Computer Science, Machine Learning
The Internet gives us access to a wealth of information in languages we don’t understand. The investigation of automated or semi-automated approaches to translation has become a thriving research ...
More
The Internet gives us access to a wealth of information in languages we don’t understand. The investigation of automated or semi-automated approaches to translation has become a thriving research field with enormous commercial potential. This book investigates how Machine Learning techniques can improve Statistical Machine Translation, currently at the forefront of research in the field. It looks first at enabling technologies—technologies that solve problems which are not Machine Translation proper but are linked closely to the development of a Machine Translation system. These include the acquisition of bilingual sentence-aligned data from comparable corpora, automatic construction of multilingual name dictionaries, and word alignment. The book then presents new or improved statistical Machine Translation techniques, including a discriminative training framework for leveraging syntactic information, the use of semi-supervised and kernel-based learning methods, and the combination of multiple Machine Translation outputs in order to improve overall translation quality.Less
The Internet gives us access to a wealth of information in languages we don’t understand. The investigation of automated or semi-automated approaches to translation has become a thriving research field with enormous commercial potential. This book investigates how Machine Learning techniques can improve Statistical Machine Translation, currently at the forefront of research in the field. It looks first at enabling technologies—technologies that solve problems which are not Machine Translation proper but are linked closely to the development of a Machine Translation system. These include the acquisition of bilingual sentence-aligned data from comparable corpora, automatic construction of multilingual name dictionaries, and word alignment. The book then presents new or improved statistical Machine Translation techniques, including a discriminative training framework for leveraging syntactic information, the use of semi-supervised and kernel-based learning methods, and the combination of multiple Machine Translation outputs in order to improve overall translation quality.
Kenji Yamada and Ion Muslea
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- chapter
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.003.0008
- Subject:
- Computer Science, Machine Learning
Statistical machine translation (SMT) systems, which are trained on parallel corpora of bilingual text (e.g., French and English), typically work as follows: for each sentence to be translated, they ...
More
Statistical machine translation (SMT) systems, which are trained on parallel corpora of bilingual text (e.g., French and English), typically work as follows: for each sentence to be translated, they generate a plethora of possible translations, from which they keep a smaller n-best list of the most likely translations. Even though the typical n-best list contains mostly high-quality candidates, the actual ranking is far from accurate. This chapter presents a novel approach to reranking the n-best list produced by an SMT system. It uses an ensemble of perceptrons that are trained in parallel, each of them on just a fraction of the available data. Experiments were performed on two large-scale commercial systems: a Chinese-to-English system trained on 80 million words and a French-to-English system trained on 1.1 billion words. The reranker obtained statistically significant improvements of about 0.5 and 0.2 BLEU points on the Chinese-to-English and the French-to-English system, respectively.Less
Statistical machine translation (SMT) systems, which are trained on parallel corpora of bilingual text (e.g., French and English), typically work as follows: for each sentence to be translated, they generate a plethora of possible translations, from which they keep a smaller n-best list of the most likely translations. Even though the typical n-best list contains mostly high-quality candidates, the actual ranking is far from accurate. This chapter presents a novel approach to reranking the n-best list produced by an SMT system. It uses an ensemble of perceptrons that are trained in parallel, each of them on just a fraction of the available data. Experiments were performed on two large-scale commercial systems: a Chinese-to-English system trained on 80 million words and a French-to-English system trained on 1.1 billion words. The reranker obtained statistically significant improvements of about 0.5 and 0.2 BLEU points on the Chinese-to-English and the French-to-English system, respectively.
Jesús Giménez and Lluís Màrquez
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- chapter
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.003.0011
- Subject:
- Computer Science, Machine Learning
This chapter explores the application of discriminative learning to the problem of phrase selection in statistical machine translation (SMT). The chapter is organized as follows. Section 11.2 ...
More
This chapter explores the application of discriminative learning to the problem of phrase selection in statistical machine translation (SMT). The chapter is organized as follows. Section 11.2 describes previous and current approaches to dedicated word selection. Section 11.3 describes the approach to discriminative phrase translation (DPT). It presents experimental results on the application of DPT models to the Spanish-to-English translation of European Parliament proceedings. In Section 11.4, prior to considering the full translation task, it measures the local accuracy of DPT classifiers at the isolated phrase translation task in which the goal is not to translate the whole sentence but only individual phrases without having to integrate their translations in the context of the target sentence. Section 11.5 tackles the full translation task while Section 11.6 summarizes the main conclusions.Less
This chapter explores the application of discriminative learning to the problem of phrase selection in statistical machine translation (SMT). The chapter is organized as follows. Section 11.2 describes previous and current approaches to dedicated word selection. Section 11.3 describes the approach to discriminative phrase translation (DPT). It presents experimental results on the application of DPT models to the Spanish-to-English translation of European Parliament proceedings. In Section 11.4, prior to considering the full translation task, it measures the local accuracy of DPT classifiers at the isolated phrase translation task in which the goal is not to translate the whole sentence but only individual phrases without having to integrate their translations in the context of the target sentence. Section 11.5 tackles the full translation task while Section 11.6 summarizes the main conclusions.
Nicola Ueffing, Gholamreza Haffari, and Anoop Sarkar
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- chapter
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.003.0012
- Subject:
- Computer Science, Machine Learning
This chapter proposes algorithms for semisupervised learning. It translates sentences from the source language and then uses them to retrain the statistical machine translation (SMT) system in the ...
More
This chapter proposes algorithms for semisupervised learning. It translates sentences from the source language and then uses them to retrain the statistical machine translation (SMT) system in the hopes of getting a better translation system. It presents detailed experimental evaluations using French-English and Chinese-English data. The French-English translation task used bilingual data from the Europarl corpus, and monolingual data from the same domain as the test set which is drawn from the Canadian Hansard corpus. The Chinese-English task used bilingual data from the NIST large-data track and monolingual data from the Chinese Gigaword corpus.Less
This chapter proposes algorithms for semisupervised learning. It translates sentences from the source language and then uses them to retrain the statistical machine translation (SMT) system in the hopes of getting a better translation system. It presents detailed experimental evaluations using French-English and Chinese-English data. The French-English translation task used bilingual data from the Europarl corpus, and monolingual data from the same domain as the test set which is drawn from the Canadian Hansard corpus. The Chinese-English task used bilingual data from the NIST large-data track and monolingual data from the Chinese Gigaword corpus.
Benjamin Wellington, Joseph Turian, and I. Dan Melamed
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- chapter
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.003.0007
- Subject:
- Computer Science, Machine Learning
This chapter presents a method for training all the parameters of a syntax-aware statistical machine translation (MT) system in a discriminative manner. The system outperforms a generative ...
More
This chapter presents a method for training all the parameters of a syntax-aware statistical machine translation (MT) system in a discriminative manner. The system outperforms a generative syntax-aware baseline. Although all the standard information sources necessary for a state-of-the-art MT system have yet to be added, but the scalability of the system suggests that the main obstacle to doing so has been overcome. The next step is to generalize the tree transducer into a bitree transducer, so that it can modify the target side of the bitree after it is inferred from the source side.Less
This chapter presents a method for training all the parameters of a syntax-aware statistical machine translation (MT) system in a discriminative manner. The system outperforms a generative syntax-aware baseline. Although all the standard information sources necessary for a state-of-the-art MT system have yet to be added, but the scalability of the system suggests that the main obstacle to doing so has been overcome. The next step is to generalize the tree transducer into a bitree transducer, so that it can modify the target side of the bitree after it is inferred from the source side.
Pierre Mahé and Nicola Cancedda
- Published in print:
- 2008
- Published Online:
- August 2013
- ISBN:
- 9780262072977
- eISBN:
- 9780262255097
- Item type:
- chapter
- Publisher:
- The MIT Press
- DOI:
- 10.7551/mitpress/9780262072977.003.0006
- Subject:
- Computer Science, Machine Learning
This chapter introduces a method for taking advantage of background linguistic resources in statistical machine translation. It starts with a brief introduction to word-sequence kernels, followed by ...
More
This chapter introduces a method for taking advantage of background linguistic resources in statistical machine translation. It starts with a brief introduction to word-sequence kernels, followed by a description of the notion of factored representation and details of the kernel formulation. The next section validates the kernel construction on an artificial discrimination task reproducing some of the conditions encountered in translation. The chapter concludes with a discussion of related and future work.Less
This chapter introduces a method for taking advantage of background linguistic resources in statistical machine translation. It starts with a brief introduction to word-sequence kernels, followed by a description of the notion of factored representation and details of the kernel formulation. The next section validates the kernel construction on an artificial discrimination task reproducing some of the conditions encountered in translation. The chapter concludes with a discussion of related and future work.