BIA: a Discriminative Phrase Alignment Toolkit
In most statistical machine translation systems, bilingual segments are extracted via word alignment. However, word alignment is performed independently from the requirements of the machine translation task. Furthermore, although phrase-based translation models have replaced word-based translation models nearly ten years ago, word-based models are still widely used for word alignment. In this paper we present the BIA (BIlingual Aligner) toolkit, a suite consisting of a discriminative phrase-based word alignment decoder based on linear alignment models, along with training and tuning tools. In the training phase, relative link probabilities are calculated based on an initial alignment. The tuning of the model weights may be performed directly according to machine translation metrics. We give implementation details and report results of experiments conducted on the Spanish-English Europarl task (with three corpus sizes), on the Chinese-English FBIS task, and on the Chinese-English BTEC task. The BLEU score obtained with BIA alignment is always as good or better than the one obtained with the initial alignment used to train BIA models. In addition, in four out of the five tasks, the BIA toolkit yields the best BLEU score of a collection of ten alignment systems. Finally, usage guidelines are presented.
Joint Phrase Alignment and Extraction for Statistical Machine Translation
