Consistency-Aware Search for Word Alignment

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1228–1237, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Consistency-Aware Search for Word Alignment Shiqi Shen†, Yang Liu†‡∗, Huanbo Luan† and Maosong Sun†‡ †State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China ‡Jiangsu Collaborative Innovation Center for Language Competence, Jiangsu, China {vicapple22,liuyang.china,luanhuanbo}@gmail.com, sms@tsinghua.edu.cn Abstract As conventional word alignment search algorithms usually ignore the consistency constraint in translation rule extraction, improving alignment accuracy does not necessarily increase translation quality. We propose to use coverage, which reflects how well extracted phrases can recover the training data, to enable word alignment to model consistency and corre- late better with machine translation. This can be done by introducing an objective that maximizes both alignment model score and coverage. We introduce an efficient algorithm to calculate coverage on the fly during search. Experiments show that our consistency-aware search algorithm significantly outperforms both generative and discriminative alignment approaches across various languages and translation models. 1 Introduction Word alignment, which aims to identify the correspondence between words in two languages, plays an important role in statistical machine translation (Brown et al., 1993). Word alignment and translation rule extraction often constitute two consecutive steps in the training pipeline. Word- aligned bilingual corpora serve as a fundamental resource for translation rule extraction, not only for phrase-based models (Koehn et al., 2003; Och and Ney, 2004), but also for syntax-based models (Chiang, 2005; Galley et al., 2006). Dividing alignment and extraction into two separate steps significantly improves the efficiency and scala- bility of parameter estimation as compared with directly learning translation models from bilingual ∗Corresponding author: Yang Liu. corpora (Marcu and Wong, 2002; DeNero and Klein, 2008; Cohn and Blunsom, 2009). However, separating word alignment from translation rule extraction suffers from a major problem: maximizing the accuracy of word align- ment does not necessarily lead to the improvement of translation quality. A number of studies show that alignment error rate (AER) only has a loose correlation with BLEU (Callison-Burch et al., 2004; Goutte et al., 2004; Ittycheriah and Roukos, 2005). Ayan and Dorr (2006) find that precision-oriented alignments result in better translation performance than recall-oriented alignments. Fraser and Marcu (2007) show that using AER and balanced F-measure can only partially explain the effect of alignment quality on BLEU for several language pairs. We believe that the correlation problem arises from the discrepancy between word alignment and translation rule extraction. On one hand, aligners seek to find the alignment with the highest alignment model score, without regard to structural constraints. Consequently, sensible translation rules may not be extracted because they violate consistency constraints required by translation rule extraction (Och and Ney, 2004). Wang et al. (2010) find that the standard alignment tools are not optimal for training syntax-based models. aligning.As a result, they have to resort to re- On the other hand, the consistency constraint used in most …

Content truncated to 500 words