文章基本信息

标题：Graded hyponymy for compositional distributional semantics
本地全文：下载
作者：Dea Bankova ; Bob Coecke ; Martha Lewis 等
期刊名称：Journal of Language Modelling
印刷版ISSN：2299-856X
电子版ISSN：2299-8470
出版年度：2018
卷号：6
期号：2
页码：225-260
DOI：10.15398/jlm.v6i2.230
语种：English
出版社：Polish Academy of Sciences
摘要：The categorical compositional distributional model of natural language provides a conceptually motivated procedure to compute the meaning of a sentence,given its grammatical structure and the mean_ings of its words.This approach has outperformed other models in mainstream empirical language processing tasks,but lacks an effec_tive model of lexical entailment.We address this shortcoming by ex?ploiting the freedom in our abstract categorical framework to change our choice of semantic model.This allows us to describe hyponymy as a graded order on meanings,using models of partial information used in quantum computation.Quantum logic embeds in this graded order.
关键词：categorical compositional distributional semantics;computational linguistics;entailment;density operator