Dialogue Act Classification, Instance-Based Learning, and Higher Order Dialogue Structure

Barbara Di Eugenio, Zhuli Xie, Riccardo Serafin


In this paper, we explore instance-based learning methods for dialogue act classification on two corpora, MapTask and CallHome Spanish. We start with Latent Semantic Analysis (LSA), and extend it as Feature Latent Semantic Analysis (FLSA). FLSA adds richer linguistic features to LSA, which only uses words. In particular, we explore the extended dialogue context, both linearly (the previous dialogue act) and hierarchically (conversational games). We show how the k-Nearest Neighbor algorithm obtains its best results when applied to the reduced semantic spaces generated by FLSA. Empirically, our results are better than previously published results on these two corpora; linguistically, we confirm and extend previous observations that the hierarchical dialogue structure encoded via the notion of Game is of primary importance for dialogue act recognition.

Full Text:


www.dialogue-and-discourse.orgISSN: 2152-9620   Journal doi: 10.5087/dad