tailieunhanh - Báo cáo khoa học: "Multi-Document Summarization of Evaluative Text"

We present and compare two approaches to the task of summarizing evaluative arguments. The first is a sentence extractionbased approach while the second is a language generation-based approach. We evaluate these approaches in a user study and find that they quantitatively perform equally well. Qualitatively, however, we find that they perform well for different but complementary reasons. We conclude that an effective method for summarizing evaluative arguments must effectively synthesize the two approaches. . | Multi-Document Summarization of Evaluative Text Giuseppe Carenini Raymond Ng and Adam Pauls Deptartment of Computer Science University of British Columbia Vancouver Canada carenini rng adpauls @ Abstract We present and compare two approaches to the task of summarizing evaluative arguments. The first is a sentence extractionbased approach while the second is a language generation-based approach. We evaluate these approaches in a user study and find that they quantitatively perform equally well. Qualitatively however we find that they perform well for different but complementary reasons. We conclude that an effective method for summarizing evaluative arguments must effectively synthesize the two approaches. 1 Introduction Many organizations are faced with the challenge of summarizing large corpora of text data. One important application is evaluative text . any document expressing an evaluation of an entity as either positive or negative. For example many websites collect large quantities of online customer reviews of consumer electronics. Summaries of this literature could be of great strategic value to product designers planners and manufacturers. There are other equally important commercial applications such as the summarization of travel logs and non-commercial applications such as the summarization of candidate reviews. The general problem we consider in this paper is how to effectively summarize a large corpora of evaluative text about a single entity . a product . In contrast most previous work on multidocument summarization has focused on factual text . news McKeown et al. 2002 biographies Zhou et al. 2004 . For factual documents the goal of a summarizer is to select the most im portant facts and present them in a sensible ordering while avoiding repetition. Previous work has shown that this can be effectively achieved by carefully extracting and ordering the most informative sentences from the original documents in a domain-independent way.