Journal article Open Access

A Multilingual Study of Multi-Sentence Compression using Word Vertex-Labeled Graphs and Integer Linear Programming

Pontes, Elvys Linhares; Huet, Stephane; Torres-Moreno, Juan-Manuel; da Silva, Thiago G.; Linhares, Andrea Carneiro

Multi-Sentence Compression (MSC) aims to generate a short sentence with the key information from a cluster of similar sentences. MSC enables summarization and question-answering systems to generate outputs combining fully formed sentences from one or several documents. This paper describes an Integer Linear Programming method for MSC using a vertex-labeled graph to select different keywords, with the goal of generating more informative sentences while maintaining their grammaticality. Our system is of good quality and outperforms the state of the art for evaluations led on news datasets in three languages: French, Portuguese and Spanish. We led both automatic and manual evaluations to determine the informativeness and the grammaticality of compressions for each dataset. In additional tests, which take advantage of the fact that the length of compressions can be modulated, we still improve ROUGE scores with shorter output sentences.

43
30
views
downloads
All versions This version
Views 4343
Downloads 3030
Data volume 7.5 MB7.5 MB
Unique views 4141
Unique downloads 2929

Share

Cite as