CAREER: Semantics for Statistical Machine Translation

在过去的几年里，随着大量平行双语文本统计系统的广泛采用，机器翻译领域发生了一场革命。最近的评估表明，目前经过统计培训的研究技术大大优于商业上可用的MT系统，如网上提供的那些系统。但是，即使是最先进的系统，也往往会产生乱码翻译。机器翻译的进一步改进将要求对统计系统的架构作出重大改变。我们的研究旨在通过允许统计系统处理更深层次的语义表示来提高机器翻译输出的质量，我们的方法侧重于通过在谓词-论元结构级别使用语义表示来改进统计机器翻译。这项工作建立在最近在浅层语言理解的统计方法方面的成功，以及使用源句子和目标句子的句法分析的基于树的机器翻译算法的基础上。在该项目的整个过程中，我们的目标是：第一，开发能够推广到新领域的健壮语义分析系统，并将其应用于大型双语语料库；第二，开发翻译的概率模型，该模型使用所产生的表示级别，并且可以进行实际训练；第三，将语言理解和翻译相结合，以便高效地搜索新句子的最佳整体翻译。

The past few years have seen a revolution in machinetranslation, with the widespread adoption ofstatistical systems trained on large amounts ofparallel bilingual text. Recent evaluations have shownthat current statistically trained research technologysignificantly outperforms commercially available MTsystems such as those available on the web. But evenstate-of-the-art systems produce garbled translationsmore often than not. Further improvements in machinetranslation will require major changes in thearchitecture of statistical systems. Our research aimsto improve the quality of machine translation output byallowing statistical systems to handle deeper, semanticrepresentations.Our approach focuses on improving statistical machinetranslation by using a semantic representation at thelevel of predicate-argument structure. This workbuilds on the recent success in statistical approachesto shallow language understanding, and tree-basedalgorithms for machine translation using syntacticparses of the source and target sentences. Over thecourse of the project we aim to: first, develop robustsemantic parsing systems capable of generalizing to newdomains and apply them to large bilingual corpora,second, develop probabilistic models of translationthat use the resulting level of representation and canbe practically trained, and third, integrate languageunderstanding and translation to allow efficient searchfor the best overall translation of new sentences.