Model adaptation for dialog act tagging
MetadataShow full item record
CitationTür, G., Güz, Ü. & Hakkani Tür, D. (2006). Model adaptation for dialog act tagging. Paper presented at the 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings, 94-97. doi:10.1109/SLT.2006.326825
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.
Source2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings
Showing items related by title, author, creator and subject.
Seyis Kazazoğlu, Senem (ASCE-AMER Soc Civil Engineers, 2019-08-01)Although a plethora of studies on building information modeling (BIM) have been conducted in the last decade, none of the previous studies collate and/or prioritize the benefits, risks, and challenges of BIM based on the ...
With the advancement of the manufacturing technologies to produce new generation analog/digital communication systems, immitance data modelling has gained renewed importance in the literature. Specifically, models are ...
An incremental model selection algorithm based on cross-validation for finding the architecture of a Hidden Markov model on hand gesture data sets In a multi-parameter learning problem, besides choosing the architecture of the learner, there is the problem of finding the optimal parameters to get maximum performance. When the number of parameters to be tuned increases, ...