CLJan 6, 2015
Un résumeur à base de graphes, indépéndant de la langue
arXiv:1501.01243v1
Originality Synthesis-oriented
AI Analysis
This addresses text summarization for NLP users, but appears incremental as it builds on existing graph-based methods without specifying novel breakthroughs.
The paper tackles automatic text summarization by proposing REG, a graph-based algorithm that maps documents to graphs and computes sentence weights, applied to documents in three languages.
In this paper we present REG, a graph-based approach for study a fundamental problem of Natural Language Processing (NLP): the automatic text summarization. The algorithm maps a document as a graph, then it computes the weight of their sentences. We have applied this approach to summarize documents in three languages.