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.

In this paper, we investigate quasi-abstractive summaries, a new type of machine-generated summaries that do not use whole sentences, but only fragments from the source. Quasi-abstractive summaries aim at bridging the gap between human-written abstracts and extractive summaries. We present an approach that learns how to identify sets of sentences, where each set contains fragments that can be used to produce one sentence in the abstract; and then uses these sets to produce the abstract itself. Our experiments show very promising results. Importantly, we obtain our best results when the summary generation is anchored by the most salient Noun Phrases predicted from the text to be summarized.