Paper: Easily Identifiable Discourse Relations

ACL ID C08-2022
Title Easily Identifiable Discourse Relations
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2008
Authors

We present a corpus study of local dis- course relations based on the Penn Dis- course Tree Bank, a large manually anno- tated corpus of explicitly or implicitly re- alized relations. We show that while there is a large degree of ambiguity in temporal explicitdiscourseconnectives, overallcon- nectives are mostly unambiguous and al- low high-accuracy prediction of discourse relation type. We achieve 93.09% accu- racy in classifying the explicit relations and 74.74% accuracy overall. In addition, we show that some pairs of relations oc- cur together in text more often than ex- pected by chance. This finding suggests that global sequence classification of the relations in text can lead to better results, especially for implicit relations.