Paper: Acquiring The Meaning Of Discourse Markers

ACL ID P04-1087
Title Acquiring The Meaning Of Discourse Markers
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2004
Authors

This paper applies machine learning techniques to acquiring aspects of the meaning of discourse mark- ers. Three subtasks of acquiring the meaning of a discourse marker are considered: learning its polar- ity, veridicality, and type (i.e. causal, temporal or additive). Accuracy of over 90% is achieved for all three tasks, well above the baselines.