Siamese Network-Based Text Semantic Matching for Multi-Document Summarization
Multi-document summarization aims to extract the sentences as a summary to best represents the central content of the document set.Text semantic matching refers to learning the semantic relationship between two text u-nits,so that the sentence representation has richer semantic information.This paper proposes a siamese network based text semantic matching for multi-document extraction summarization.This method combines siamese network and pre-training model BERT to construct a joint learning model of text semantic matching and text summarization.The model uses the twin network to examine the semantic association between any two text units from different per-spectives,learns the fragmented information in the document set,and finally combines the text summary model to select the main content of the document set.The experimental results show that compared with the current main-stream multi-document extractive summarization method,this method has a substantial improvement in the ROUGE index.
multi-document extractive summarizationsemantic relationpre-training language model
万方数据
维普
