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...

A fundamental requirement of any task-oriented dialogue system is the ability to generate object descriptions that refer to objects in the task domain. The subproblem of content selection for object descriptions in task-oriented dialogue has been the focus of much previous work and a large number of models have been proposed. In this paper, we use the annotated coconut corpus of task-oriented design dialogues to develop feature sets based on Dale and Reiter’s (1995) incremental model, Brennan and Clark’s (1996) conceptual pact model, and Jordan’s (2000b) intentional influences model, and use these feature sets in a machine learning experiment to automatically learn a model of content selection for object descriptions. Since Dale and Reiter’s model requires a representation of discourse structure, the corpus annotations are used to derive a representation based on Grosz and Sidner’s (1986) theory of the intentional structure of discourse, as well as two very simple representations of discourse structure based purely on recency. We then apply the rule-induction program ripper to train and test the content selection component of an object description generator on a set of 393 object descriptions from the corpus. To our

In this paper, we present the results of a corpus analysis, and a model of anaphora resolution in spontaneous spoken dialogues in the form of an algorithm. The main finding of our corpus analysis is that less than half the pronouns and demonstratives have NP antecedents in the preceding text. 22% have sentential antecedents and the remainder have no identifiable linguistic antecedents. As part of the corpus analysis we present the results of interannotator agreement tests. These were carried out for marking anaphor types and their antecedents, and for segmenting the dialogues into dialogue acts. The results of the inter-annotator agreement tests indicate that our classification method is reliable and that the annotated dialogues can be used as a standard against which to measure the performance of the resolution algorithm. The algorithm, based on Strube (1998), is capable of classifying pronouns and demonstratives, and co-indexing anaphors with NP and sentential antecedent...

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...

In this paper we discuss the use of multi-layered tagsets for dialogue acts, in the context of dialogue understanding for multiparty meeting recording and retrieval applications. We discuss

The structure of a discourse is reflected in many as- pects of its linguistic realization, including its lexical, prosodic, syntacfic, and semantic nature. Multiparty dialog contains a particular kind of discourse structure, the dialog act (DA). Like other types of structure, the dialog act sequence of a conversation is also reflected in its lexical, prosodic, and syntactic realization. This paper presents a preliminary investigation into the realization of a particular class of dialog acts which play an essential structuring role in dialog, the backchannels or acknowledge- merits tokens. We discuss the lexical, prusodic, and syntactic realization of these and subsumer or re- lated dialog acts like continuers, assessments, yes. answers, agreements, and incipient-speakership. We show that lexical knowledge plays a role in distinguishing these dialog acts, despite the widespread ambiguity of words such as yeah, and that prosodic knowledge plays a role in DA identifica- tion for certain DA types, while lexical cues may be sufficient for the remainder. Finally, our investi- gation of the syntax of assessments suggests that at least some dialog acts have a very constrained syntactic realization, a per-dialog act 'microsyntax'.

The ability to request clarification of utterances is a vital part of the communicative process. In this paper we discuss the range of possible forms for clarification requests, together with the range of readings they can convey. We present the results of corpus analysis which show a correlation between certain forms and possible readings, together with some indication of maximum likely distance between request and the utterance being clarified.

There is currently a broad interest in dialogue acts and dialogue act taxonomies, and new uses, taxonomies, and standardization efforts continue to be proposed. This paper presents a discussion of issues that must be addressed in order to facilitate the shared understanding and use of taxonomies. The discussion is framed in terms of 20 questions, the answers to which will help make the meanings of taxonomy elements more clear to different communities of users.

ion from explicit choices . This mainly covers explicit disjunctions. At the meta level (a) Shall we begin from the living room or from the dining room can be abstracted as start from room, where the parameter room can be instantiated as living room or dining room. The disjunction could also regard the actions itself, rather than parameters of a single action: (a) Should we color coordinate or match furniture? At the domain level, let's consider (a) I have a red sofa for 150 or a blue one for 200 The underlying action in (a) (in the appropriate context, i.e., excluding the exhaustive listing reading discussed below) is buy sofa, where the parameter sofa can be instantiated either as my red sofa for 150 or my blue sofa for 200. It will be tagged as Assert, Open-Option, Offer. 4 Rule of thumb: general actions will be tagged as an Open-Option in their Influence-on-Listener aspect; and they will not be tagged along the Influence-on-Speaker aspect. No action. When the coder can individua...

Abstract. This paper presents the results of initial investigation and experiments into automatic action item detection from transcripts of multi-party human-human meetings. We start from the flat action item annotations of [1], and show that automatic classification performance is limited. We then describe a new hierarchical annotation schema based on the roles utterances play in the action item assignment process, and propose a corresponding approach to automatic detection that promises improved classification accuracy while also enabling the extraction of useful information for summarization and reporting. 1