Paper: Discourse Chunking: A Tool In Dialogue Act Tagging

ACL ID P03-2009
Title Discourse Chunking: A Tool In Dialogue Act Tagging
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2003
Authors

Discourse chunking is a simple way to segment dialogues according to how dia- logue participants raise topics and negoti- ate them. This paper explains a method for arranging dialogues into chunks, and also shows how discourse chunking can be used to improve performance for a dialogue act tagger that uses a case-based reasoning approach. 1 Dialogue act tagging A dialogue act (hereafter DA) is an encapsulation of the speaker�s intentions in dialogue�what the speaker is trying to accomplish by saying some- thing. In DA tagging (similar to part-of-speech tagging), utterances in a dialogue are tagged with the most appropriate speech act from a tagset. DA tagging has application in NLP work, including speech recognition and language understanding. The Verbmobil-2 corpus was used for this st...