tailieunhanh - Báo cáo khoa học: "A Comparison of Head Transducers and Transfer for a Limited Domain Translation Application"

We compare the effectiveness of two related • machine translation models applied to the same limited-domain task. One is a transfer model with monolingual head automata for analysis and generation; the other is a direct transduction model based on bilingual head transducers. We conclude that the head transducer model is more effective according to measures of accuracy, computational requirements, model size, and development effort. | A Comparison of Head Transducers and Transfer for a Limited Domain Translation Application Hiyan Alshawi and Adam L. Buchsbaum AT T Labs 180 Park Avenue FLorham Park. NJ 07932-0971. USA @research. Abstract We compare the effectiveness of two related machine translation models applied to the same limited-domain task. One is a transfer model with monolingual head automata for analysis and generation the other is a direct transduction model based on bilingual head transducers. We conclude that the head transducer model is more effective according to measures of accuracy computational requirements model size and development effort. 1 Introduction In this paper we describe an experimental machine translation system based on head transducer models and compare it to a related transfer system described in Alshawi 1996a based on monolingual head automata. Head transducer models consist of collections of finite state machines that are associated with pairs of lexical items in a bilingual lexicon. The transfer system follows the familiar analysis-transfer-generation architecture Isabelle and Macklovitch 1986 . with mapping of dependency representations Hudson 1984 in the transfer phase. In contrast the head transducer approach is more closely aligned with earlier direct translation methods no explicit representations of the source language interlingua or otherwise are created in the process of deriving the target string. Despite the simple direct architecture the head transducer model does embody modern principles of lexicalized recursive grammars and statistical language processing. The context for evaluating both the transducer and transfer models was the development of experimental prototypes for speech-to-speech translation. In the case of text translation for publishing it is reasonable to adopt economic measures of the Fei Xia Department of Computer and Information Science University of Pennsylvania Philadelphia. PA 19104. USA fxia@ .