Measuring the Effect of Discourse Relations on Blog Summarization

TL;DR

This paper evaluates how different discourse relations impact blog summarization, finding that some relations significantly improve summary quality across informal blogs and traditional news texts.

Contribution

It quantifies the usefulness of six discourse relations in blog summarization and compares their effects to traditional texts, highlighting which relations enhance content.

Findings

Contingency, comparison, and illustration relations improve summarization.

Discourse relations are as useful for blogs as for news articles.

Some relations do not consistently improve summarization quality.

Abstract

The work presented in this paper attempts to evaluate and quantify the use of discourse relations in the context of blog summarization and compare their use to more traditional and factual texts. Specifically, we measured the usefulness of 6 discourse relations - namely comparison, contingency, illustration, attribution, topic-opinion, and attributive for the task of text summarization from blogs. We have evaluated the effect of each relation using the TAC 2008 opinion summarization dataset and compared them with the results with the DUC 2007 dataset. The results show that in both textual genres, contingency, comparison, and illustration relations provide a significant improvement on summarization content; while attribution, topic-opinion, and attributive relations do not provide a consistent and significant improvement. These results indicate that, at least for summarization, discourse relations are just as useful for informal and affective texts as for more traditional news articles.