Dimensionality of dialogue act tagsets

作者: Andrei Popescu-Belis

DOI: 10.1007/S10579-008-9063-Y

关键词:

摘要: This article compares one-dimensional and multi-dimensional dialogue act tagsets used for automatic labeling of utterances. The influence tagset dimensionality on tagging accuracy is first discussed theoretically, then based empirical data from human annotations large scale resources, using four existing tagsets: damsl, swbd-damsl, icsi-mrda maltus. Dominant Function Approximation proposes that taggers could focus initially finding the main function each utterance, which empirically acceptable has significant practical relevance.

参考文章(16)
M. Sandra Carberry, Kenneth Brian Samuel, Vijay K. Shanker, Discourse learning: an investigation of dialogue act tagging using transformation-based learning University of Delaware. ,(2000)
Elizabeth Shriberg, Raj Dhillon, Sonali Bhagat, Jeremy Ang, Hannah Carvey, The ICSI Meeting Recorder Dialog Act (MRDA) Corpus annual meeting of the special interest group on discourse and dialogue. pp. 97- 100 ,(2004) , 10.21236/ADA460980
Andrei Popescu-Belis, Alexander Clark, Multi-level Dialogue Act Tags annual meeting of the special interest group on discourse and dialogue. pp. 163- 170 ,(2004)
Christopher D. Manning, Hinrich Schütze, Foundations of Statistical Natural Language Processing ,(1999)
Harry Bunt, Dynamic Interpretation and Dialogue Theory The Structure of Multimodal Dialogue, Vol. 2. pp. 139- 188 ,(2000)
D. R. TRAUM, 20 Questions on Dialogue Act Taxonomies Journal of Semantics. ,vol. 17, pp. 7- 30 ,(2000) , 10.1093/JOS/17.1.7
Christine Doran, John Aberdeen, Laurie Damianos, Lynette Hirschman, Comparing several aspects of human-computer and human-human dialogues Proceedings of the Second SIGdial Workshop on Discourse and Dialogue -. pp. 1- 10 ,(2001) , 10.3115/1118078.1118085
Jan van Kuppevelt, Ronnie W. Smith, Matthew Stone, Current and New Directions in Discourse and Dialogue Computational Linguistics. ,vol. 30, pp. 521- 524 ,(2004) , 10.1162/0891201042544910