Logical and Stochastic Approaches to Mismatch Resolution in Machine Translation

机器翻译中解决不匹配问题的逻辑和随机方法

• 批准号: 9628880
• 负责人: Jean Mark Gawron
• 金额: $ 39.5万
• 依托单位: SRI International
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1996
• 资助国家: 美国
• 起止时间: 1996-10-15 至 2001-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9628880&HistoricalAwards=false
• 关键词: Logical; Stochastic; Approaches; Mismatch; Resolution

A major bottleneck in present-day machine translation (MT) is identifying appropriate approximations when no exact translation exists between the source and target languages. An MT system must resolve mismatches either by incorporating implicit information from context or leaving out some information in the source text. A prototype MT system is implemented, incorporating the usual MT steps, analysis (analyzing English sources into an English-oriented semantic representation), transfer (transferring the English-oriented semantics into a Japanese-oriented semantics), and generation (building Japanese targets from the transferred semantics), and adding a novel Mismatch Resolution Module (MRM) called when generation fails. In this architecture, both analysis and generation modules are purely monolingual, and transfer is simplistic, incorporating minimal context information, and the bulk of mismatch resolution and disambiguation is done in the generation-MRM loop, where the MRM offers solutions to the problems encountered by generation. Two kinds of MRMs are explored, logical and statistical, with the design goal of a single MRM combining the advantages of both approaches. Translations are evaluated by monolingual English speakers applying evaluation measures modeled on those of the DARPA MT program. The focus is on translating the Japanese joint venture business articles in the MUC-5 corpus into English. This project attacks the crucial mismatch resolution problem with a novel architecture, logical and statistical techniques, and on-line text resources.

当前机器翻译的一个主要瓶颈是在源语言和目标语言之间不存在精确翻译的情况下识别合适的近似。机器翻译系统必须通过合并上下文中的隐含信息或省略源文本中的一些信息来解决不匹配问题。实现了一个原型机器翻译系统，该系统结合了常用的机器翻译步骤，包括分析(分析英语源到面向英语的语义表示)、转换(将面向英语的语义转换为面向日语的语义)和生成(从转换后的语义构建日语目标)，并增加了一个新的失配解决模块(MRM)，当生成失败时称为MRM。在该体系结构中，分析和生成模块都是纯单语的，传输是简单的，合并了最少的上下文信息，并且大部分失配解决和歧义消除在生成-MRM循环中完成，在该循环中，MRM为生成遇到的问题提供解决方案。探讨了逻辑型和统计型两种MRM，其设计目标是将两种方法的优点结合起来形成单一的MRM。翻译由只会说一种语言的人按照DARPA机器翻译项目的评估标准进行评估。重点是将MUC-5语料库中的日本合资企业商务文章翻译成英语。该项目以一种新颖的架构、逻辑和统计技术以及在线文本资源来解决关键的不匹配问题。