Achieving commercial-quality translation with example-based methods
نویسندگان
چکیده
We describe MSR-MT, a large-scale example-based machine translation system under development for several language pairs. Trained on aligned English-Spanish technical prose, a blind evaluation shows that MSR-MT’s integration of rule-based parsers, example based processing, and statistical techniques produces translations whose quality in this domain exceeds that of uncustomized commercial MT systems.
منابع مشابه
Problems with the second generation architecture and new trends in MT
In this tutorial presentation, we will first consider the characteristics of the typical “second generation” rule-based architecture for MT, and suggest some of the drawbacks of this approach, including development effort, robustness, scalability, and translation quality. There will be some discussion of the second-generation architecture and comparison with the architecture it was supposed to ...
متن کاملShallow-transfer rule-based machine translation for Swedish to Danish
This article describes the development of a shallow-transfer machine translation system from Swedish to Danish in the Apertium platform. It gives details of the resources used, the methods for constructing the system and an evaluation of the translation quality. The quality is found to be comparable with that of current commercial systems, despite the particularly low coverage of the lexicons.
متن کاملOvercoming the customization bottleneck using example-based MT
We describe MSR-MT, a large-scale hybrid machine translation system under development for several language pairs. This system’s ability to acquire its primary translation knowledge automatically by parsing a bilingual corpus of hundreds of thousands of sentence pairs and aligning resulting logical forms demonstrates true promise for overcoming the so-called MT customization bottleneck. Trained ...
متن کاملForest Rescoring: Faster Decoding with Integrated Language Models
Efficient decoding has been a fundamental problem in machine translation, especially with an integrated language model which is essential for achieving good translation quality. We develop faster approaches for this problem based on k-best parsing algorithms and demonstrate their effectiveness on both phrase-based and syntax-based MT systems. In both cases, our methods achieve significant speed...
متن کاملCan we make do with Near Human Quality?
This paper discusses the acceptability of Near Human Quality machine translation. It defines Near Human Quality and provides examples of cases where Near Human Quality machine translation is acceptable. The paper assumes that there are programs capable of generating Near Human Quality output after some customization. The purpose of this paper is to discuss the acceptability of Near Human Qualit...
متن کامل