M\'etodos de Otimiza\c{c}\~ao Combinat\'oria Aplicados ao Problema de Compress\~ao MultiFrases

TL;DR

This paper introduces a novel combinatorial optimization and graph theory-based method for multi-sentence compression that improves informativeness and grammaticality, outperforming existing state-of-the-art approaches.

Contribution

It presents a new approach combining combinatorial optimization and graph theory for multi-sentence compression, enhancing sentence informativeness and grammaticality.

Findings

Achieved higher quality in sentence compression compared to existing methods.

Demonstrated effectiveness on a corpus of 40 sentence clusters.

Outperformed state-of-the-art techniques in experiments.

Abstract

The Internet has led to a dramatic increase in the amount of available information. In this context, reading and understanding this flow of information have become costly tasks. In the last years, to assist people to understand textual data, various Natural Language Processing (NLP) applications based on Combinatorial Optimization have been devised. However, for Multi-Sentences Compression (MSC), method which reduces the sentence length without removing core information, the insertion of optimization methods requires further study to improve the performance of MSC. This article describes a method for MSC using Combinatorial Optimization and Graph Theory to generate more informative sentences while maintaining their grammaticality. An experiment led on a corpus of 40 clusters of sentences shows that our system has achieved a very good quality and is better than the state-of-the-art.