arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv cs/0106011cs.CLcs.HC
收藏

基于环境的消歧的计算特性

Computational properties of environment-based disambiguation

William Schuler

摘要:

语义处理的标准流水线方法(其中句子在被解释之前在形态和句法上被解析为单个树)不太适合自然语言接口等应用。这是因为环境信息,在应用程序的运行时环境中的对象和事件的形式,不能被用来通知解析决策,除非输入句子进行语义分析,但这不会发生,直到在单树语义架构解析。本文介绍了一种替代架构的计算性能,在解析过程中,在多项式时间对所有可能的解释进行语义分析。

英文摘要:

The standard pipeline approach to semantic processing, in which sentences are morphologically and syntactically resolved to a single tree before they are interpreted, is a poor fit for applications such as natural language interfaces. This is because the environment information, in the form of the objects and events in the application's run-time environment, cannot be used to inform parsing decisions unless the input sentence is semantically analyzed, but this does not occur until after parsing in the single-tree semantic architecture. This paper describes the computational properties of an alternative architecture, in which semantic analysis is performed on all possible interpretations during parsing, in polynomial time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑