Which Embedding Level is Better for Semantic Representation? An Empirical Research on Chinese Phrases

摘要：

　　Word embeddings have been used as popular features in various Natural Language Processing(NLP)tasks.To overcome the coverage problem of statistics,compositional model is proposed,which embeds basic units of a language,and compose structures of higher hierarchy,like idiom,phrase,and named entity.In that case,selecting the right level of basic-unit embedding to represent semantics of higher hierarchy unit is crucial.This paper investigates this problem by Chinese phrase representation task,in which language characters and words are viewed as basic units.We define a phrase representation evaluation tasks by utilizing Wikipedia.We propose four intuitionistic composing methods from basic embedding to higher level representation,and investigate the performance of the two basic units.Empirical results show that with all composing methods,word embedding out performs character embedding on both tasks,which indicates that word level is more suitable for composing semantic representation.

关键词： Word embedding Phrase representation Composing model

作者: Kunyuan Pang Jintao Tang Ting Wang

作者单位: College of Computer,National University of Defense Technology Changsha,Hunan410073,Peoples Republic of China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 54-66

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）