arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1403.2152cs.CLcs.NE
收藏

使用词关联向量语法的语法分析

Parsing using a grammar of word association vectors

Robert John Freeman

摘要:

本文于2001年首次起草,作为美国专利US 7,392,174中描述的系统的形式化。它描述了一种基于上下文相似词向量的叉积来实现解析器的系统。它现在正在发布,以响应对语法和语义的向量组合模型的新生兴趣。该方法使用上下文相似的单词和词组的积极替代,使产品向量保持在与其操作数相同的空间中,并使整个句子在句法上和潜在的语义上具有可比性。生成的向量有足够的代表性强度生成解析树至少与当代符号解析器。

英文摘要:

This paper was was first drafted in 2001 as a formalization of the system described in U.S. patent U.S. 7,392,174. It describes a system for implementing a parser based on a kind of cross-product over vectors of contextually similar words. It is being published now in response to nascent interest in vector combination models of syntax and semantics. The method used aggressive substitution of contextually similar words and word groups to enable product vectors to stay in the same space as their operands and make entire sentences comparable syntactically, and potentially semantically. The vectors generated had sufficient representational strength to generate parse trees at least comparable with contemporary symbolic parsers.

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。

↑