Multi-engine machine translation guided by explicit word matching

EAMT 2005 Conference Proceedings 143 Multi-Engine Machine Translation Guided by Explicit Word Matching Shyamsundar Jayaraman and Alon Lavie Language Technologies Institute, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh PA 15213 USA {shyamj, alavie}@cs.cmu.edu Abstract. We describe a new approach for synthetically combining the output of several different Machine Translation (MT) engines operating on the same input. The goal is to pro- duce a synthetic combination that surpasses all of the original systems in translation quality. Our approach uses the individual MT engines as “black boxes” and does not require any explicit cooperation from the original MT systems. An explicit word matcher is first used in order to identify the words that are common between the MT engine outputs. A decoding algorithm then uses this information, in conjunction with confidence estimates for the vari- ous engines and a trigram language model in order to score and rank a collection of sen- tence hypotheses that are synthetic combinations of words from the various original en- gines. The highest scoring sentence hypothesis is selected as the final output of our system. Experiments conducted using three Chinese-to-English online translation systems demon- strate that our multi-engine combination system provides an improvement of about 6% over the best original system, and is about equal in translation quality to an “oracle” capable of selecting the best of the original systems on a sentence-by-sentence basis. A second oracle experiment shows that our new approach produces synthetic combination sentence hy- potheses that are far superior to the hypotheses currently selected by the system, but our current scoring is not yet capable of adequately identifying the best hypothesis. 1. Introduction A variety of different paradigms for machine translation (MT) have been developed over the years, ranging from statistical systems that learn mappings between words and phrases in the source language and their corresponding trans- lations in the target language, to Interlingua- based systems that perform deep semantic analy- sis. All of these approaches have well-known advantages and disadvantages. Corpus-based sys- tems, such as statistical machine translation and example-based machine translation, provide broad coverage but rarely produce translations of qual- ity that is comparable to that achieved by knowl- edge-based systems, which involve deeper syn- tactic and semantic analysis. Knowledge-Based systems that incorporate syntactic and semantic knowledge provide high-quality translations but require large amounts of human time to create and rarely have the coverage of corpus-based systems. With such a wide range of approaches to ma- chine translation, it would be beneficial to have an effective framework for combining these systems into an MT system that carries many of the advantages of the individual systems and suffers from few of their disadvantages. Attempts at combining outputs from different systems have proved useful in other areas of language technologies, such as the ROVER approach for speech recognition (Fiscus 1997). Several dif- ferent multi-engine machine translation (MEMT) systems have also been explored in the past ten years, starting with the Pangloss system in 1994 (Frederking and Nirenburg). Several of these sys- tems require …

Content truncated to 500 words