期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2014
卷号：3
期号：9
页码：8009-8011
出版社：IJECS
摘要：We present a probabilistic generative model for learning semantic parsers from ambiguous supervision. Our approach learnsfrom natural language sentences paired with world states consisting of multiple potential logical meaning representations. It disambiguatesthe meaning of each sentence while simultaneously learning a semantic parser that maps sentences into logical form. Compared to aprevious generative model for semantic alignment, it also supports full semantic parsing
关键词：reranking; syntactic parsing; semantic parsing; semantic role labeling ; named entity recognition
