Abstractive Summarization Improved by WordNet-Based Extractive Sentences

摘要：

　　Recently,the seq2seq abstractive summarization models have achieved good results on the CNN/Daily Mail dataset.Still,how to improve abstractive methods with extractive methods is a good research direction,since extractive methods have their potentials of exploiting various efficient features for extracting important sentences in one text.In this paper,in order to improve the semantic relevance of abstractive summaries,we adopt the WordNet based sentence ranking algorithm to extract the sentences which are most semantically to one text.Then,we design a dual attentional seq2seq framework to generate summaries with consideration of the extracted information.At the same time,we combine pointer-generator and coverage mechanisms to solve the problems of out-of-vocabulary(OOV)words and duplicate words which exist in the abstractive models.Experiments on the CNN/Daily Mail dataset show that our models achieve competitive performance with the state-of-theart ROUGE scores.Human evaluations also show that the summaries generated by our models have high semantic relevance to the original text.

关键词： Abstractive summarization Seq2seq model Dual attention Extractive summarization WordNet

作者: Niantao Xie Sujian Li Huiling Ren Qibin Zhai

作者单位: MOE Key Laboratory of Computational Linguistics,Peking University,Beijing,China Institute of Medical Information,Chinese Academy of Medical Sciences,Beijing,China MOE Information Security Lab,School of Software and Microelectronics,Peking University,Beijing,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: 404-415

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）