Inducing Chinese Selectional Preference Based on HowNet
Computational Intelligence and Security（2011）
摘要
Selectional preference (SP) is an important semantic knowledge. It can be used in various natural language processing tasks, including metaphor computing, lexicon building, syntactic structure disambiguation, word sense disambiguation, semantic role labeling, etc. However, handcrafted SP knowledge can not meet the requirement of large scale real text processing. Based on the noun taxonomy of How Net, this paper proposes a statistical and knowledge-based method to automatically induce Chinese SP. Preliminary experimental results show that the automatically acquired SP agree well with human judgment.
更多查看译文
关键词
lexicon building,semantic knowledge,handcrafted sp knowledge,hownet,knowledge based systems,semantic role labeling,various natural language processing,human judgment,selectional association,statistical analysis,important semantic knowledge,chinese selectional preference,chinese sp,natural language processing tasks,selectional preference,inducing chinese selectional preference,real text processing,text processing,knowledge acquisition,knowledge based method,metaphor computing,syntactic structure disambiguation,statistical based method,noun taxonomy,natural language processing,word sense disambiguation,semantic role,semantics,hidden markov models,hidden markov model,knowledge base,taxonomy,knowledge based system,computational modeling,noun,computer model
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要