Discourse Processing of Dialogues with Multiple Threads

  title={Discourse Processing of Dialogues with Multiple Threads},
  author={Carolyn Penstein Ros{\'e} and Barbara Maria Di Eugenio and Lori S. Levin and Carol Van Ess-Dykema},
In this paper we will present our ongoing work on a plan-based discourse processor developed in the context of the Enthusiast Spanish to English translation system as part of the JANUS multi-lingual speech-to-speech translation system. We will demonstrate that theories of discourse which postulate a strict tree structure of discourse on either the intentional or attentional level are not totally adequate for handling spontaneous dialogues. We will present our extension to this approach along… 

Figures from this paper

Discourse-Level Dialogue Management

This Chapter explains how to build an invariant discourse tree for a corpus of texts to arrange a chatbot-facilitated navigation through this corpus, and introduces imaginary discourse tree to address a problem of involving background knowledge on demand, answering questions.

Dialogue processing in a conversational speech translation system

This paper describes how the JANUS multi-lingual speech-to-speech translation system addresses problems that arise in discourse processing of spontaneous speech, and describes robust parsers, procedures for segmenting long utterances, and two approaches to discourse processing that attempt to deal with ambiguity and cumulative error.

Applications of discourse structure for spoken dialogue systems

This research investigates the utility of discourse structure for spoken dialogue systems in more complex domains, e.g. tutoring, and finds statistical dependencies between discourse structure transitions and two dialogue phenomena which allow us to speculate where and why these dialogue phenomena occur and to better understand system behavior.

Conventions in human-human multi-threaded dialogues: a preliminary study

It is found that some subjects are able to vary where they switch depending on how urgent the interrupting task is, and they switched at the end of a discourse segment, which is hypothesized to be less disruptive to the interrupted task when it is later resumed.

multithreaded context for robust conversational interfaces: Context-sensitive speech recognition and interpretation of corrective fragments

It is shown that by using context-sensitive recognition based on the predicted type of the user's next dialogue move, a more flexible dialogue system can also exhibit an improvement in speech recognition performance.

Coherence maintenance in human-machine dialogue: indirect antecedents and ellipses

A heuristic algorithm for detection of the indirect antecedents for dialogue phrases based on the use of a dictionary of prototypic scenarios associated with each headword, as well as of a thesaurus of the standard type is presented.

Conversational Actions and Discourse Situations

We use the idea that actions performed in a conversation become part of the common ground as the basis for a model of context that reconciles in a general and systematic fashion the differences

Input Segmentation of Spontaneous Speech in JANUS: A Speech-to-speech Translation System

This paper describes how multi-level segmentation of single utterance turns improves translation quality and facilitates accurate translation in the Janus speech-to-speech translation system.

Modeling Task-Oriented Dialogue

The use of a finite state machine (FSM) to disambiguate speech acts in a machinetranslation system and Evaluation results show that the discourse processor is able todisambiguates and improve the quality of thedialogue translation.

Using Discourse Predictions for Ambiguity Resolution

This paper discusses how discourse predictions along with non context-based predictions to the problem of parse disambiguation in Enthusiast, a Spanish-to-English translation system, and evaluates extensions to the plan-based discourse processor in order to make this possible.



Speech--Language Integration In A Multi--Lingual Speech Translation System

An overview of the task databases and the system architecture will focus on how speech decoding and natural language processing modules will be integrated in a large scale multi lingual speech to speech translation system for spontaneous spoken discourse.

Recognizing complex discourse acts: a tripartite plan-based model of dialogue

An algorithm is presented that combines world, linguistic, and contextual knowledge to recognize complex discourse acts such as expressing doubt and that enables the system to model the structure of negotiation dialogues, a step towards a complete model of negotiation and thus a more robust model of understanding.

The Structure of Multiple-Headed Negotiations

In this paper I demonstrate that theories which postulate a strict tree structure of discourse on either the intentional or attentional level are not totally adequate for handling spontaneous

An Augmented Context Free Grammar for Discourse

This paper presents an augmented context free grammar which describes important features of the surface structure and the semantics of discourse in a formal way, integrating new as well as previously

Linguistic and pragmatic constraints on utterance interpretation

This document presents a method of speech act interpretation which uses patterns of linguistic features to identify a range ofspeech act interpretations for the utterance, and explains how "Can you pass the salt?" can be a request while "Are you able to pass the Salt?" is not.

Informational redundancy and resource bounds in dialogue

This thesis argues that IRUs can only be explained by a processing model of dialogue that re ects agents autonomy and limited attentional and inferential capacity, and that the com municative function of IRUs is related to the cognitive properties of resource limited agents.

Structure and Ostension in the Interpretation of Discourse Deixis

It is argued that a restricted set of discourse segments yield what such demonstrative pronouns can point to in the discourse model and arestricted set of what Nunberg (1979) has called referring functions yield what they can refer to by virtue of that pointing.

Attention, Intentions, and the Structure of Discourse

A new theory of discourse structure that stresses the role of purpose and processing in discourse is explored and various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored.

A formal model of the structure of discourse

Using collaborative plans to model the intentional structure of discourse

A computational model for recognizing intentional structure and utilizing it in discourse processing is provided that satisfies the requirements of Grosz and Sidner's (1986) theory of discourse structure and also simplifies and extends previous plan-based approaches to dialogue understanding.