Dialogue Act Recognition using Reweighted Speaker Adaptation

In this work we study the effectiveness of speaker adaptation for dialogue act recognition in multiparty meetings. First, we analyze idiosyncracy in dialogue verbal acts by qualitatively studying the differences and conflicts among speakers and by quantitively comparing speaker-specific models. Based on these observations, we propose a new approach for dialogue act recognition based on reweighted domain adaptation which effectively balance the influence of speaker specific and other speakers’ data. Our experiments on a realworld meeting dataset show that with even only 200 speaker-specific annotated dialogue acts, the performances on dialogue act recognition are significantly improved when compared to several baseline algorithms. To our knowledge, this work is the first 1 to tackle this promising research direction of speaker adaptation for dialogue act recogntion.