Clause restructuring for statistical machine translation

2013

We describe a novel approach to combining lexicalized, POS-based and syntactic treebased word reordering in a phrase-based machine translation system. Our results show that each of the presented reordering methods leads to improved translation quality on its own. The strengths however can be combined to achieve further improvements. We present experiments on German-English and GermanFrench translation. We report improvements of 0.7 BLEU points by adding tree-based and lexicalized reordering. Up to 1.1 BLEU points can be gained by POS and tree-based reordering over a baseline with lexicalized reordering. A human analysis, comparing subjective translation quality as well as a detailed error analysis show the impact of our presented tree-based rules in terms of improved sentence quality and reduction of errors related to missing verbs and verb positions.

Proceedings of the NAACL-HLT 2007/AMTA Workshop on Syntax and Structure in Statistical Translation - SSST '07, 2007

In this paper, we describe a sourceside reordering method based on syntactic chunks for phrase-based statistical machine translation. First, we shallow parse the source language sentences. Then, reordering rules are automatically learned from source-side chunks and word alignments. During translation, the rules are used to generate a reordering lattice for each sentence. Experimental results are reported for a Chinese-to-English task, showing an improvement of 0.5%-1.8% BLEU score absolute on various test sets and better computational efficiency than reordering during decoding. The experiments also show that the reordering at the chunk-level performs better than at the POS-level.

2006

This paper proposes the use of rules automatically extracted from word aligned training data to model word reordering phenomena in phrase-based statistical machine translation. Scores computed from matching rules are used as additional feature functions in the rescoring stage of the automatic translation process from various languages to English, in the ambit of a popular traveling domain task. Rules are defined either on Part-of-Speech or words. Part-of-Speech rules are extracted from and applied to Chinese, while lexicalized rules are extracted from and applied to Chinese, Japanese and Arabic. Both Part-of-Speech and lexicalized rules yield an absolute improvement of the BLEU score of 0.4-0.9 points without affecting the NIST score, on the Chinese-to-English translation task. On other language pairs which differ a lot in the word order, the use of lexicalized rules allows to observe significant improvements as well.

2008

Reordering is of crucial importance for machine translation. Solving the reordering problem can lead to remarkable improvements in translation performance. In this paper, we propose a novel approach to solve the word reordering problem in statistical machine translation. We rely on the dependency relations retrieved from a statistical parser incorporating with linguistic hand-crafted rules to create the transformations. These dependency-based transformations can produce the problem of word movement on both phrase and word reordering which is a difficult problem on parse tree based approaches. Such transformations are then applied as a preprocessor to English language both in training and decoding process to obtain an underlying word order closer to the Vietnamese language. About the hand-crafted rules, we extract from the syntactic differences of word order between English and Vietnamese language. This approach is simple and easy to implement with a small rule set, not lead to the rule explosion. We describe the experiments using our model on VCLEVC corpus [18] and consider the translation from English to Vietnamese, showing significant improvements about 2-4% BLEU score in comparison with the MOSES phrase-based baseline system [19].

2014

Word reordering is a difficult task for translation. Common automatic metrics such as BLEU have problems reflecting improvements in target language word order. However, it is a crucial aspect for humans when deciding on translation quality. This paper presents a detailed analysis of a structure-aware reordering approach applied in a German-to-English phrase-based machine translation system. We compare the translation outputs of two translation systems applying reordering rules based on parts-of-speech and syntax trees on a sentence-by-sentence basis. For each sentence-pair we examine the global translation performance and classify local changes in the translated sentences. This analysis is applied to three data sets representing different genres. While the improvement in BLEU differed substantially between the data sets, the manual evaluation showed that both global translation performance as well as individual types of improvements and degradations exhibit a similar behavior throug...

We present a method for improving statistical machine translation performance by using linguistically motivated syntactic information. Our algorithm recursively decomposes source language sentences into syntactically simpler and shorter chunks, and recomposes their translation to form target language sentences. This improves both the word order and lexical selection of the translation. We report statistically significant relative improvements of 3.3% BLEU score in an experiment (English→Spanish) carried out on an 800-sentence test set extracted from the Europarl corpus.

We describe an approach to automatic source-language syntactic preprocessing in the context of Arabic-English phrase-based machine translation. Source-language labeled dependencies, that are word aligned with target language words in a parallel corpus, are used to automatically extract syntactic reordering rules in the same spirit of and . The extracted rules are used to reorder the source-language side of the training and test data. Our results show that when using monotonic decoding and translations for unigram source-language phrases only, source-language reordering gives very significant gains over no reordering (25% relative increase in BLEU score). With decoder distortion turned on and with access to all phrase translations, the differences in BLEU scores are diminished. However, an analysis of sentence-level BLEU scores shows reordering outperforms no-reordering in over 40% of the sentences. These results suggest that the approach holds big promise but much more work on Arabic parsing may be needed.

International Journal of Computer Processing of Languages, 2007

We present a phrase-based SMT approach in which the wordorder problem is solved using syntactic transformation in the preprocessing phase (There is no reordering in the decoding phase.) We describe a syntactic transformation model based on the probabilistic context-free grammar. This model is trained by using bilingual corpus and a broad coverage parser of the source language. This phrase-based SMT approach is applicable to language pairs in which the target language is poor in resources. We considered translation from English to Vietnamese and from English to French. Our experiments showed significant BLEU-score improvements in comparison with Pharaoh, a state-of-the-art phrase-based SMT system.

2010

This paper describes the techniques we explored to improve the translation of news text in the German-English and Hungarian-English tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, and incorporation of a feature scoring the alignment of function words in the hypothesized translation. We also explored the use of monolingual paraphrases to improve coverage, as well as co-training to improve the quality of the segmentation lattices used, but these did not lead to improvements.

2009

This paper describes the techniques we explored to improve the translation of news text in the German-English and Hungarian-English tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, and incorporation of a feature scoring the alignment of function words in the hypothesized translation. We also explored the use of monolingual paraphrases to improve coverage, as well as co-training to improve the quality of the segmentation lattices used, but these did not lead to improvements.