LexRank: Graph-based Lexical Centrality as Salience in Text Summarization

TL;DR

LexRank introduces a graph-based eigenvector centrality method for extractive text summarization, outperforming other techniques and demonstrating robustness to data noise in large datasets.

Contribution

The paper presents LexRank, a novel eigenvector centrality approach for sentence importance in summarization, outperforming centroid-based methods and showing robustness to noise.

Findings

LexRank outperforms other methods in DUC evaluations.

Degree-based methods outperform centroid-based methods.

LexRank with threshold is the most effective degree-based technique.

Abstract

We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences. In this model, a connectivity matrix based on intra-sentence cosine similarity is used as the adjacency matrix of the graph representation of sentences. Our system, based on LexRank ranked in first place in more than one task in the recent DUC 2004 evaluation. In this paper we present a detailed analysis of our approach and apply it to a larger data set including data from earlier DUC evaluations. We discuss several methods to compute centrality using the similarity graph. The results show that degree-based methods (including LexRank) outperform both centroid-based methods and other systems participating in DUC in most of the cases. Furthermore, the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. We also show that our approach is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents.