DIALOGUE-ACT TAGGING USING SMART FEATURE SELECTION; RESULTS ON MULTIPLE CORPORA
- 1 January 2006
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2006 IEEE Spoken Language Technology Workshop
Abstract
This paper presents an overview of our on-going work on dialogue-act classification. Results are presented on the ICSI, switchboard, and on a selection of the AMI corpus, setting a baseline for forthcoming research. For these corpora the best accuracy scores obtained are 89.27%, 65.68% and 59.76%, respectively. We introduce a smart compression technique for feature selection and compare the performance from a subset of the AMI transcriptions with AMI-ASR output for the same subset.Keywords
This publication has 6 references indexed in Scilit:
- A* based joint segmentation and classification of dialog acts in multiparty meetingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Textual data categorization: back to the phrase-based representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- The ICSI Meeting CorpusPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A shallow model of backchannel continuers in spoken dialoguePublished by Association for Computational Linguistics (ACL) ,2003
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational SpeechComputational Linguistics, 2000
- SWITCHBOARD: telephone speech corpus for research and developmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992