An Unsupervised Approach to Recognizing Discourse Relations
Abstract
We present an unsupervised approach to recognizing discourse relations of CONTRAST, EXPLANATION-EVIDENCE, CONDITION and ELABORATION that hold between arbitrary spans of texts. We show that discourse relation classifiers trained on examples that are automatically extracted 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 explicitly marked by cue phrases.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2002
- Accession Number
- ADA462240
Entities
People
- Abdessamad Echihabi
- Daniel Marcu
Organizations
- University of Southern California