EAGER: Formal and Empirical Foundations of Semantics-Preserving Machine Translation

EAGER：保留语义的机器翻译的形式和经验基础

• 批准号: 1349902
• 负责人: Adam Lopez
• 金额: $ 14.99万
• 依托单位: Johns Hopkins University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-08-15 至 2015-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1349902&HistoricalAwards=false
• 关键词: EAGER; Formal; Empirical; Foundations; Semantics

Statistical machine translation has been enormously successful over the last two decades, resulting in what is today a thriving industry highlighted by offerings such as Google Translate. Yet translation systems still often fail to preserve the semantics of sentences -- the "who did what to whom" relationships that they express. This is because they model translation as simple substitution and permutation of words, or at best as the reordering of syntactic units, such as nouns and adjectives. To preserve semantics, they must model semantics. At the same time, computational linguists have developed rigorous, expressive mathematical models of language that exhibit high empirical coverage of semantically annotated linguistic data, correctly predict a variety of important linguistic phenomena in many languages, and can be processed with highly efficient algorithms. However, these models are untested as the basis of statistical translation models. This EArly Grant for Exploratory Research aims to close the gap, building the foundations of empirical semantics-preserving transduction models based on modern, linguistically-informed mathematical models of language. The project derives new mathematical functions that map linguistically expressive representations from one language to another, and implement them to align translated documents and translate new documents. Though high-risk, this exploratory project has the potential to unify and transform the disparate fields of empirical machine translation and theoretical computational linguistics.

在过去的二十年里，统计机器翻译取得了巨大的成功，导致了一个今天蓬勃发展的行业，谷歌翻译等服务凸显了这一行业的繁荣。然而，翻译系统仍然常常无法保留句子的语义--它们所表达的“谁对谁做了什么”的关系。这是因为他们将翻译建模为单词的简单替换和排列，或者充其量是对句法单位的重新排序，如名词和形容词。为了保留语义，它们必须对语义进行建模。与此同时，计算语言学家开发了严格的、富有表现力的语言数学模型，这些模型展示了对带语义注释的语言数据的高经验覆盖率，正确地预测了许多语言中的各种重要语言现象，并且可以使用高效的算法进行处理。然而，这些模型并未作为统计翻译模型的基础进行检验。这项早期的探索性研究拨款旨在弥合这一差距，为基于现代语言数学模型的经验语义保留转导模型奠定基础。该项目推导出新的数学函数，将语言表达形式从一种语言映射到另一种语言，并实施它们以对齐翻译的文档和翻译新的文档。尽管风险很高，但这一探索性项目有可能统一和改变经验机器翻译和理论计算语言学的不同领域。