TY - GEN
T1 - Model adaptation for dialog act tagging
AU - Tur, Gokhan
AU - Guz, Umit
AU - Hakkani-Tür, Dilek
PY - 2006
Y1 - 2006
N2 - In this paper, we analyze the effect of model adaptation for dialog act tagging. The goal of adaptation is to improve the performance of the tagger using out-of-domain data or models. Dialog act tagging aims to provide a basis for further discourse analysis and understanding in conversational speech. In this study we used the ICSI meeting corpus with high-level meeting recognition dialog act (MRDA) tags, that is, question, statement, backchannel, disruptions, and floor grabbers/holders. We performed controlled adaptation experiments using the Switchboard (SWBD) corpus with SWBD-DAMSL tags as the out-of-domain corpus. Our results indicate that we can achieve significantly better dialog act tagging by automatically selecting a subset of the Switchboard corpus and combining the confidences obtained by both in-domain and out-of-domain models via logistic regression, especially when the in-domain data is limited.
AB - In this paper, we analyze the effect of model adaptation for dialog act tagging. The goal of adaptation is to improve the performance of the tagger using out-of-domain data or models. Dialog act tagging aims to provide a basis for further discourse analysis and understanding in conversational speech. In this study we used the ICSI meeting corpus with high-level meeting recognition dialog act (MRDA) tags, that is, question, statement, backchannel, disruptions, and floor grabbers/holders. We performed controlled adaptation experiments using the Switchboard (SWBD) corpus with SWBD-DAMSL tags as the out-of-domain corpus. Our results indicate that we can achieve significantly better dialog act tagging by automatically selecting a subset of the Switchboard corpus and combining the confidences obtained by both in-domain and out-of-domain models via logistic regression, especially when the in-domain data is limited.
UR - http://www.scopus.com/inward/record.url?scp=48749111525&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=48749111525&partnerID=8YFLogxK
U2 - 10.1109/SLT.2006.326825
DO - 10.1109/SLT.2006.326825
M3 - Conference contribution
AN - SCOPUS:48749111525
SN - 1424408733
SN - 9781424408733
T3 - 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings
SP - 94
EP - 97
BT - 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings
T2 - 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006
Y2 - 10 December 2006 through 13 December 2006
ER -