Litcius/Paper detail

Read Top News First: A Document Reordering Approach for Multi-Document News Summarization

Chao Zhao, Tenghao Huang, Somnath Basu Roy Chowdhury, Muthu Kumar Chandrasekaran, Kathleen McKeown, Snigdha Chaturvedi

2022Findings of the Association for Computational Linguistics: ACL 202213 citationsDOIOpen Access PDF

Abstract

A common method for extractive multidocument news summarization is to reformulate it as a single-document summarization problem by concatenating all documents as a single meta-document. However, this method neglects the relative importance of documents. We propose a simple approach to reorder the documents according to their relative importance before concatenating and summarizing them. The reordering makes the salient content easier to learn by the summarization model. Experiments show that our approach outperforms previous state-of-the-art methods with more complex architectures.

Topics & Concepts

Automatic summarizationComputer scienceInformation retrievalMulti-document summarizationSalientSimple (philosophy)Natural language processingArtificial intelligenceEpistemologyPhilosophyTopic ModelingNatural Language Processing TechniquesAdvanced Text Analysis Techniques
Read Top News First: A Document Reordering Approach for Multi-Document News Summarization | Litcius