A Multilingual Study of Multi-Sentence Compression using Word Vertex-Labeled Graphs and Integer Linear Programming
Abstract: 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.
| Main Authors: | , , , , |
|---|---|
| Format: | Digital revista |
| Language: | English |
| Published: |
Instituto Politécnico Nacional, Centro de Investigación en Computación
2020
|
| Online Access: | http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1405-55462020000200897 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract: 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. |
|---|