Collaborative Research: Structure Alignment-based Machine Translation

合作研究：基于结构对齐的机器翻译

• 批准号: 0534700
• 负责人: Adam Meyers
• 金额: --
• 依托单位: New York University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2006
• 资助国家: 美国
• 起止时间: 2006-07-01 至 2010-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0534700&HistoricalAwards=false
• 关键词: Collaborative; Research; Structure; Alignment; based

Researchers at New York University, Monmouth University and theUniversity of Colorado are constructing Japanese/English andChinese/English machine translation systems which automatically acquirerules from ``deep'' linguistic analyses of parallel text. This workis a natural culmination of automated example-based MachineTranslation (MT) projects that have become increasingly sophisticatedover the last two decades. The following recent advances in NaturalLanguage Processing (NLP) technologies make this inquiry feasible: (1)annotated data including bilingual treebanks and processors trained onthis data (parsers, PropBankers, etc.); (2) semantic post-processorsof parser output; (3) programs that automatically align bitexts; and(4) bilingual tree to tree translation models.Natural languages vary widely in the ordering of corresponding wordsfor equivalent expressions across linguistic boundaries and within asingle language. This research investigates ways to minimize thevariations within a single language using a type of semanticrepresentation (GLARF) that is derived automatically from syntactictrees. Such semantic representation provides for: (1) a reduction in thenumber of ways of representing the same underlying message, and (2)a way to handle long distance dependencies (e.g. relativeclauses) as local phenomena. Therefore, there is no need to resort toarbitrarily long sentence fragments or large trees fortraining. Furthermore, since less data is needed, itminimizes the sparse data problem.In the training of this translation model, because of (1), the numberof mapping rules between the source tree and the target tree isreduced. The translation model, then, is a tree transducer, with``deep'' linguistically analyzed trees for both source and targetrepresentations. In order to provide efficient computer algorithmsfor such partial mappings, this research needs to focus on(a) the training algorithm and the (b) the constraints over themapping rules in order to reduce the computational complexity.This research is expected to yield several advantages: The corearchitecture of this transducer using ``deep'' linguistic analysesshould yield more accurate results. The GLARF architecture allowscontrol over different granularity of automatically-obtainedlinguistic analyses.Broader Impact: The demand for machine translation spans from thelocal government (e.g. police forces) to national government(e.g. CIA) and the private sector. Given the growth of the Internetoutside the English speaking world, better machine translation is ofcritical importance for the broader community. This work directlyaffects the ability of English speakers to understand websites writtenin Chinese and Japanese, two of the most widely used languages on theInternet. The technique is generalizable to other language pairs andcan ultimately have even wider impact.

纽约大学、蒙茅斯大学和科罗拉多大学的研究人员正在构建日/英和中/英机器翻译系统，这些系统可以从平行文本的“深层”语言分析中自动获取规则。 这项工作是自动化的基于示例的机器翻译（MT）项目的自然高潮，在过去的二十年里，这些项目已经变得越来越成熟。自然语言处理（NaturalLanguage Processing，NLP）技术的下列最新进展使这种研究成为可能：（1）注释数据，包括双语树库和在此数据上训练的处理器（解析器，PropBankers等）; (2)语义分析器输出的后处理器;（3）自动对齐双文本的程序;（4）双语树到树翻译模型。自然语言在跨语言边界和单一语言内的等效表达的相应单词的顺序方面有很大差异。本研究探讨如何尽量减少在一个单一的语言使用一种类型的语义表示（GLARF），自动从语法树派生的变化。这样的语义表示提供：（1）减少表示相同底层消息的方式的数量，以及（2）将长距离依赖性（例如，相对子句）作为局部现象处理的方式。因此，没有必要求助于任意长的句子片段或大树进行训练。此外，由于所需的数据较少，它最大限度地减少了稀疏数据问题。在该翻译模型的训练中，由于（1），减少了源树和目标树之间的映射规则的数量。 因此，翻译模型是一个树转换器，具有针对源和目标表示的“深度”语言分析树。 为了给这种部分映射提供有效的计算机算法，本研究需要关注（a）训练算法和（B）映射规则的约束以降低计算复杂度。GLARF架构允许控制自动获得的语言分析的不同粒度。更广泛的影响：对机器翻译的需求从地方政府（例如警察部队）到国家政府（例如CIA）和私营部门。 考虑到英语世界以外的互联网的发展，更好的机器翻译对更广泛的社区至关重要。 这项工作直接影响到英语使用者理解中文和日文网站的能力，中文和日文是互联网上使用最广泛的两种语言。这项技术可以推广到其他语言对，并最终产生更广泛的影响。