摘要
该文首先介绍一个逼近文本蕴涵关系的推理模型,它由带有推理规则集的蕴涵型式知识库和相关的概率评价构成。接着介绍习得推理规则和蕴涵型式及其概率的几种方法,包括从平行或单一语料库中学习和从网络文件中学习。然后介绍基于词汇概率的蕴涵识别模型,包括通过构建词汇蕴涵的概率模型和基于词汇所指的语义匹配模型来逼近文本蕴涵的几种方法。最后介绍基于句法的语义分析模型,包括基于依存树节点匹配、论元结构或原子命题匹配等处理模型。
This article firstly presents an inference model that consists of a knowledge base of entailment patterns a- long with a set of inference rules and related probability estimations, which approximates the textual entailment rela- tionship and predicates whether an entailment holds for a given text-hypothesis pair. Then it introduces some meth- ods of learning the inference rules and entailment patterns and their probability, including learning from a single or parallel/comparable corpus, or from the web. Finally, it describes the recognizing entailment models which based on lexical probability, e.g. lexical entailment probability models and lexical reference matching models, and the syntax and semantics driven models, e.g. the models based on the matching the dependency tree nodes or predicate-argu- ment structures between a given text-hypothesis pair.
出处
《中文信息学报》
CSCD
北大核心
2010年第2期3-13,共11页
Journal of Chinese Information Processing
基金
国家社会科学基金资助项目(07AYY00A)
国家863高技术发展计划资助项目(2007AA01Z173)
关键词
计算机应用
中文信息处理
文本蕴涵
推理模型
蕴涵型式
识别模型
词汇概率
句法语义
computer application
Chinese information processing
textual entailment ： inference model
entailment pattern
recognizing models
lexical probability
syntax and semantics
