Enhance Content Selection for Multi-Document Summarization with Entailment Relation

Automatic text summarization is one of the common tasks in natural language processing. The main task is to generate a shorter version based on the original text and maintain relevant information. This paper studies multi-document summarization (MDS) that applies to news articles. MDS has two significant issues which are information overlap and information difference among multiple articles. Existing models mostly deal with MDS from the perspective of single document summarization (SDS). The models do not consider the relation between sentences in multiple news articles. Our proposed method deals with the issue and consists of two models. The sentence selector model selects representative sentences based on the entailment relation in different articles. The content is related to the event of the article extracted through the algorithm. The summary generator model generates a final summary to ensure that the summary contains no redundancy and maintains vital information. Experiment results show that our proposed model has effectively improved in the evaluation results. The main contribution of our approach is to use the entailment relation to obtain key content in multiple articles. Adding semantic comprehension can identify salient information clearly and improve the accuracy of MDS.