Effective Phrase Translation Extraction from Alignment Models

Effective Phrase Translation Extraction from Alignment Models Ashish Venugopal Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213 ashishv@cs.cmu.edu Stephan Vogel Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213 vogel+@cs.cmu.edu Alex Waibel Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213 ahw@cs.cmu.edu Abstract Phrase level translation models are ef- fective in improving translation qual- ity by addressing the problem of local re-ordering across language boundaries. Methods that attempt to fundamentally modify the traditional IBM translation model to incorporate phrases typically do so at a prohibitive computational cost. We present a technique that begins with im- proved IBM models to create phrase level knowledge sources that effectively repre- sent local as well as global phrasal con- text. Our method is robust to noisy align- ments at both the sentence and corpus level, delivering high quality phrase level translation pairs that contribute to signif- icant improvements in translation quality (as measured by the BLEU metric) over word based lexica as well as a competing alignment based method. 1 Introduction Statistical Machine Translation defines the task of translating a source language sentence ��� ����� � into a target language sentence ��  � ��� . The traditional framework presented in (Brown et al., 1993) assumes a generative process where the source sentence is passed through a noisy stochastic process to produce the target sentence. The task can be formally stated as finding the   s.t   =    ��! �" where the search compo- nent is commonly referred to as the decoding step (Wang and Waibel, 1998). Within the generative model, the Bayes reformulation is used to estimate �#! � %$ � ��&! ' where �' is considered the lan- guage model, and ��&!  is the translation model; the IBM (Brown et al., 1993) models being the de facto standard. Direct translation approaches (Fos- ter, 2000) consider estimating ��! �" directly, and work by (Och and Ney, 2002) show that similar or improved results are achieved by replacing ��! ' in the optimization with �#! � , at the cost of devi- ating from the Bayesian framework. Regardless of the approach, the question of accurately estimating a model of translation from a large parallel or com- parable corpus is one of the defining components within statistical machine translation. Re-ordering effects across languages have been modeled in several ways, including word-based (Brown et al., 1993), template-based (Och et al., 1999) and syntax-based (Yamada, Knight, 2001). Analyzing these models from a generative mind- set, they all assume that the atomic unit of lexi- cal content is the word, and re-ordering effects are applied above that level. (Marcu, Wong, 2002) il- lustrate the effects of assuming that lexical corre- spondence can only be modeled at the word level, and motivate a joint probability model that explic- itly generates phrase level lexical content across both languages. (Wu, 1995) presents a bracketing method that models re-ordering at the sentence level. Both (Marcu, Wong, 2002; Wu, 1995) model the re- ordering phenomenon effectively, …

Content truncated to 500 words