Paper: An Unsupervised Approach To Recognizing Discourse Relations

ACL ID P02-1047
Title An Unsupervised Approach To Recognizing Discourse Relations
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2002
Authors

We present an unsupervised approach to recognizing discourse relations of CON- TRAST, EXPLANATION-EVIDENCE, CON- DITION and ELABORATION that hold be- tween arbitrary spans of texts. We show that discourse relation classifiers trained on examples that are automatically ex- tracted from massive amounts of text can be used to distinguish between some of these relations with accuracies as high as 93%, even when the relations are not ex- plicitly marked by cue phrases.