We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speec-act-like

Identifying whether an utterance is a statement, question, greeting, and so forth is integral to effective automatic understanding of natural dialog. Little is known, however, about how such dialog acts (DAs) can be automatically classified in truly natural conversation. This study asks whether current approaches, which use mainly word information, could be improved by adding prosodic information. The study is based on more than 1000 conversations from the Switchboard corpus. DAs were handannotated, and prosodic features (duration, pause, F0, energy, and speaking rate) were automatically extracted for each DA. In training, decision trees based on these features were inferred

We describe a new approach for statistical modeling and detection of discourse structure for natural conversational speech. Our model is based on 42 'Dialog Acts' (DAs), (question, answer, backchannel, agreement, disagreement, apology, etc). We labeled 1155 conversations from the Switchboard (SWBD) database (Godfrey et al. 1992) of human-to-human telephone conversations with these 42 types and trained a Dialog Act detector based on three distinct knowledge sources: sequence of words which characterize a dialog act, prosodic features which characterize a dialog act, and a statistical Discourse Grammar. Our combined detector, although still in preliminary stages, already achieves a 65% Dialog Act detection rate based on acoustic waveforms, and 72% accuracy based on word transcripts. Using this detector to switch among the 42 Dialog-Act-Specific trigram LMs also gave us an encouraging but not statistically significant reduction in SWBD word error.

We describe a new approach for statistical modeling and detection of discourse structure for natural conversational speech. Our model is based on 42 `Dialog Acts' (DAs), (question, answer, backchannel, agreement, disagreement, apology, etc). We labeled 1155 conversations from the Switchboard (SWBD) database (Godfrey et al. 1992) of human-to-human telephone conversations with these 42 types and trained a Dialog Act detector based on three distinct knowledge sources: sequences of words which characterize a dialog act, prosodic features which characterize a dialog act, and a statistical Discourse Grammar. Our combined detector, although still in preliminary stages, already achieves a 65% Dialog Act detection rate based on acoustic waveforms, and 72% accuracy based on word transcripts. Using this detector to switch among the 42 dialog-act-specific trigram LMs also gave us an encouraging but not statistically significant reduction in SWBD word error. 1 Introduction The ability to model and...

We describe an integrated approach for statistical modeling of discourse structure for natural conversational speech. Our model is based on 42 `dialog acts' (e.g., Statement, Question, Backchannel, Agreement, Disagreement, Apology), which were hand-labeled in 1155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We developed several models and algorithms to automatically detect dialog acts from transcribed or automatically recognized words and from prosodic properties of the speech signal, and by using a statistical discourse grammar. All of these components were probabilistic in nature and estimated from data, employing a variety of techniques (hidden Markov models, N-gram language models, maximum entropy estimation, decision tree classifiers, and neural networks). In preliminary studies, we achieved a dialog act labeling accuracy of 65% based on recognized words and prosody, and an accuracy of 72% based on word transcripts. Since humans achiev...

We propose the first unsupervised approach to the problem of modeling dialogue acts in an open domain. Trained on a corpus of noisy Twitter conversations, our method discovers dialogue acts by clustering raw utterances. Because it accounts for the sequential behaviour of these acts, the learned model can provide insight into the shape of communication in a new medium. We address the challenge of evaluating the emergent model with a qualitative visualization and an intrinsic conversation ordering task. This work is inspired by a corpus of 1.3 million Twitter conversations, which will be made publicly available. This huge amount of data, available only because Twitter blurs the line between chatting and publishing, highlights the need to be able to adapt quickly to a new medium. 1

This paper describes a probabilistic method for dialogue act #DA# extraction for concept-based multilingual translation systems. ADA is a unit of a semantic interlingua and it consists of speaker information, speech act, concept and argument. Probabilistic models for the extraction of speech acts or concepts are trained as speech act or concept dependent word n-gram models. The proposed method is evaluated on DA-annotated English and Japanese databases. The experimental results show that the proposed method gives a better performance compared to the conventioanl grammar -based approach. In addition, the proposed method is much more robust for erroneous inputs obtained as speech recognition outputs. 1. INTRODUCTION In the C-STAR #Consortium for Speech Translation Advanced Research# project, several sites of spoken language groups, i.e., at CMU, ATR , UKA, ETRI, IRST 1 , etc. are developing multilingual speech-to-speech translation systems #1##2##3#. To facilitate multilingual transl...

Introduction These days there's a computational version of everything. Computational biology, computational musicology, computational archaeology, and so on, ad infinitum. Even movies are going digital. This chapter, as you might have guessed by now, thus explores the computational side of pragmatics. Computational pragmatics might be defined as the computational study of the relation between utterances and context. Like other kinds of pragmatics, this means that computational pragmatics is concerned with indexicality, with the relation between utterances and action, with the relation between utterances and discourse, and with the relationship between utterances and the place, time, and environmental context of their being uttered. As Bunt and Black (2000) point out, computational pragmatics, like pragmatics in general, is especially concerned with INFERENCE. Four core inferential problems in pragmatics have received the most attention in the computational com

We introduce a statistical model for dialogues. We describe a dynamic programming algorithm that can be used to bracket a dialogue into segments and label each segment with its speech act. We evaluate the performance of the model. We also use this model for language modelling and get perplexity reduction. 1

Acknowledgements I would like to take this opportunity to thank all the people who have helped me with my research and thus made this work possible. First of all, I am very grateful to my advisor, Alexander Rudnicky, for his valuable guidance and support throughout the course of this work and my graduate school career. His vision and understanding in scientific research teach me all the elements I would need to know when conducting high quality research on my own. I am also sincerely grateful to my committee members, William Cohen, Carolyn Penstein Rosé, and Gokhan Tür, for their valuable suggestions and contributions to this research. Carolyn Penstein Rosé in particular gave me a great deal of feedback on the thesis writing. While at CMU, I have been lucky enough to be a part of a friendly and very helpful research community. I would like to thank my fellow research group members and the members of the Dialogs on Dialogs reading group, Dan Bohus, Antoine Raux, Mihai Rotaru, Banerjee Satanjeev, Stefanie Tomko, and many other people that I would not be possible to list all their names here, for numerous intellectual discussions and their