Hierarchical Phrase-Based Translation Grammars Extracted from Alignment Posterior Probabilities

Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 545–554, MIT, Massachusetts, USA, 9-11 October 2010. c⃝2010 Association for Computational Linguistics Hierarchical Phrase-based Translation Grammars Extracted from Alignment Posterior Probabilities Adri`a de Gispert, Juan Pino, William Byrne Machine Intelligence Laboratory Department of Engineering, University of Cambridge Trumpington Street, CB2 1PZ, U.K. {ad465|jmp84|wjb31}@eng.cam.ac.uk Abstract We report on investigations into hierarchi- cal phrase-based translation grammars based on rules extracted from posterior distributions over alignments of the parallel text. Rather than restrict rule extraction to a single align- ment, such as Viterbi, we instead extract rules based on posterior distributions provided by the HMM word-to-word alignment model. We define translation grammars progressively by adding classes of rules to a basic phrase-based system. We assess these grammars in terms of their expressive power, measured by their ability to align the parallel text from which their rules are extracted, and the quality of the translations they yield. In Chinese-to-English translation, we find that rule extraction from posteriors gives translation improvements. We also find that grammars with rules with only one nonterminal, when extracted from posteri- ors, can outperform more complex grammars extracted from Viterbi alignments. Finally, we show that the best way to exploit source-to- target and target-to-source alignment models is to build two separate systems and combine their output translation lattices. 1 Introduction Current practice in hierarchical phrase-based trans- lation extracts regular phrases and hierarchical rules from word-aligned parallel text. Alignment models estimated over the parallel text are used to generate these alignments, but these models are then typically used no further in rule extraction. This is less than ideal because these alignment models, even if they are not suitable for direct use in translation, can still provide a great deal of useful information beyond a single best estimate of the alignment of the parallel text. Our aim is to use alignment models to generate the statistics needed to build translation grammars. The challenge in doing so is to extend the current procedures, which are geared towards the use of a single alignment, to make more of what can be pro- vided by alignment models. The goal is to extract a richer and more robust set of translation rules. There are two aspects to hierarchical phrase-based translation grammars which concern us. The first is expressive power, which we take as the ability to generate known reference translations from sen- tences in the source language. This is determined by the degree of phrase movements and the trans- lations allowed by the rules of the grammar. For a grammar with given types of rules, larger rule sets will yield greater expressive power. This motivates studies of grammars based on the rules which are ex- tracted and the movement the grammar allows. The second aspect is of course translation accuracy. If the expressive power is adequate, then the desire is that the grammar assigns a high score to a correct translation. We use posterior probabilities over parallel data to address both of these …

Content truncated to 500 words