We present a method for improving word alignment quality for phrase-based statistical machine translation by reordering the source text according to the target word order suggested by an initial word alignment. The reordered text is used to create a second word alignment which can be an improvement of the first alignment, since the word order is more similar. The method requires no other pre-processing such as part-of-speech tagging or parsing. We report improved Bleu scores for English-to-German and English-to-Swedish translation. We also examined the effect on word alignment quality and found that the reordering method increased recall while lowering precision, which partly can explain the improved Bleu scores. A manual evaluation of the translation output was also performed to understand what effect our reordering method has on the translation system. We found that where the system employing reordering differed from the baseline in terms of having more words, or a different word order, this generally led to an improvement in translation quality.

Word alignment gold standards are an importantresource for developing and evaluatingword alignment methods. In thispaper we present a free English–Swedishword alignment gold standard consistingof texts from Europarl with manually verifiedword alignments. The gold standardcontains two sets of word aligned sentences,a test set for the purpose of evaluationand a training set that can be usedfor supervised training. The guidelinesused for English–Swedish alignment werecreated based on guidelines for other languagepairs and with statistical machinetranslation as the targeted application. Wealso present results of intrinsic evaluationusing our gold standard and discuss the relationshipto extrinsic evaluation in a statisticalmachine translation system.

This paper presents the LIU system for the WMT 2011 shared task for translation between German and English. For English– German we attempted to improve the translation tables with a combination of standard statistical word alignments and phrase-based word alignments. For German–English translation we tried to make the German text more similar to the English text by normalizing German morphology and performing rule-based clause reordering of the German text. This resulted in small improvements for both translation directions.

We present a novel approach to query reformulation which combines syntactic and semantic information by means of generalized Levenshtein distance algorithms where the substitution operation costs are based on probabilistic term rewrite functions. We investigate unsupervised, compact and efficient models, and provide empirical evidence of their effectiveness. We further explore a generative model of query reformulation and supervised combination methods providing improved performance at variable computational costs. Among other desirable properties, our similarity measures incorporate information-theoretic interpretations of taxonomic relations such as specification and generalization.

In this paper we report on experiments with three preprocessing strategies for improving translation output in a statistical MT system. In training, two reordering strategies were studied: (i) reorder on thebasis of the alignments from Giza++, and (ii) reorder by moving all verbs to the end of segments. In translation, out-of-vocabulary words were preprocessed in a knowledge-lite fashion to identify a likely equivalent. All three strategies were implemented for our English-German systems submitted to the WMT10 shared task. Combining them lead to improvements in both language directions.

We describe the LIU systems for English-German and German-English translation in the WMT09 shared task. We focus on two methods to improve the word alignment: (i) by applying Giza++ in a second phase to a reordered training corpus, where reordering is based on the alignments from the first phase, and (ii) by adding lexical data obtained as high-precision alignments from a different word aligner. These methods were studied in the context of a system that uses compound processing, a morphological sequence model for German, and a part-of-speech sequence model for English. Both methods gave some improvements to translation quality as measured by Bleu and Meteor scores, though not consistently. All systems used both out-of-domain and in-domain data as the mixed corpus had better scores in the baseline configuration.

We describe the LIU systems for German-English and English-German translation submitted to the Shared Task of the Third Workshop of Statistical Machine Translation. The main features of the systems, as compared with the baseline, is the use of morphological pre- and post-processing, and a sequence model for German using morphologically richparts-of-speech. It is shown that these additions lead to improved translations.