Pragmatic interpretation and dialogue management in spoken-language systems (original) (raw)
Related papers
Speech Dialogue Systems: A" Pragmatics-First" Approach to Rational Interaction
Modelling rational dialogues on the basis of Finite-State Automata has shown to be of limited use when natural speech behaviour and dynamic adaptation to new domains are an issue. To enable such a flexible, robust and generic dialogue management, we rely on an approach characterized by a logically precise modelling of the linguistic and application aspects of the domain in question and a dialogue manager deriving pragmaticsdriven discourse strategies from reasoning on evolving belief structures, both of the user and the system. The feedback cycle between the dialogue manager and the applications is of vital importance, as is the close interaction on the linguistic side occurring between the speech parser, the dialogue manager and the text generation module.
An architecture for spoken dialogue management
4th International Conference on Spoken Language Processing (ICSLP 1996), 1996
We propose an architecture for integrating discourse processing and speech recognition (SR) in spoken dialogue systems. It was first developed for computer-mediated bilingual dialogue in voiceto-voice machine translation applications and we apply it here to a distributed battlefield simulation system used for military training. According to this architecture discourse functions previously distributed through the interface code are collected into a centralized discourse capability. The Dialogue Manager (DM) acts as a third-party mediator overseeing the translation of input and output utterances between English and the command language of the backend system. The DM calls the Discourse Processor (DP) to update the context representation each time an utterance is issued or when a salient non-linguistic event occurs in the simulation. The DM is responsible for managing the interaction among components of the interface system and the user. For task-based human-computer dialogue systems it consults three sources of nonlinguistic context constraint in addition to the linguistic Discourse State: (1) a User Model, (2) a static Domain Model containing rules for engaging the backend system, with a grammar for the language of well-formed, executable commands, and (3) a dynamic Backend Model (BEM) that maintains updated status for salient aspects of the non-linguistic context. In this paper we describe its four-step recovery algorithm invoked by DM whenever an item is unclear in the current context, or when an interpretation error is, and show how parameter settings on the algorithm can modify the overall behavior of the system from Tutor to Trainer. This is offered to illustrate how limited (inexpensive) dialogue processing functionality, judiciously selected, and designed in conjunction with expectations for human dialogue behavior can compensate for inevitable limitations in SR, NL processor, the backend software application, or even in the user's understanding of the task or the software system.
Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, 1998
This paper details a software architecture for discourse processing in spoken dialogue systems, where the three component tasks of discourse processing are (1) Dialogue Management, (2) Context Tracking, and (3) Pragmatic Adaptation. We define these three component tasks and describe their roles in a complex, near-future scenario in which multiple humans interact with each other and with computers in multiple, simultaneous dialogue exchanges. This paper reports on the software modules that accomplish the three component tasks of discourse processing, and an architecture for the interaction among these modules and with other modules of the spoken dialogue system. A motivation of this work is reusable discourse processing software for integration with non-discourse modules in spoken dialogue systems. We document the use of this architecture and its components in several prototypes, and also discuss its potential application to spoken dialogue systems defined in the near-future scenario.
This paper describes the dialogue layer of a Spoken Dialogue System prototype. We have developed a methodology for the design of dialogue management systems following Knowledge Engineering principles. A dialogue is treated as an activity that requires knowledge, experience, ability and training. We will also propose a specification language for the representation of the linguistic knowledge involved, as well as a task-oriented inference engine for the control and reasoning about the dialogue. This generic model has been implemented in Delfos, an application developed for the automatic telephone task scenario.
Speech Dialogue Systems - A Pragmatics-Guided Approach to Rational Interaction
The general goal in implementing dialogue systems is in most cases to provide some kind of human-computer-interface for rational interaction. For that purpose, an approach is required which enables such a system to satisfy user goals in a given (ideally open) domain by conducting spoken dialogues. Furthermore, it should be possible to augment it by other kinds of multi-modal interaction like gestures or the selection of items from a menu on a screen. Interactions are called "rational" because rationality principles, at the knowledge representation level, should be applied to optimally select appropriate communicative actions. In this article, di erent approaches to the understanding of dialogues and the implementation of dialogue systems will be presented. As a basis for comparing the approaches, fundamental issuses of language understanding, speech act theory, and theories of rational interaction are outlined. To give an impression of their implications for the implementa...
A pragmatic confirmation mechanism for an object-based spoken dialogue manager
Using a relatively simple confirmation strategy based on confirmation statuses, discourse pegs and request templates it is possible to implement an effective mixed initiative, natural language dialogue system. If the basic confirmation strategy is inherited by a set of specialist domain objects, the approach becomes particularly useful, allowing dialogues in several business areas to be conducted in a single implementation. The following paper outlines the basic confirmation mechanism and illustrates how this can be augmented by 'rules of thumb' that are encapsulated in implemented domain experts and that recommend particular strategies for continuing a transaction, given particular combinations of confirmed and unconfirmed information.
On-line Interpretation in Speech Understanding and Dialogue Systems
Recent Advances in Speech Understanding and Dialog Systems, 1988
This paper addresses syntactic, semantic and pragmatic aspects of central concern in the design of on-line language understanding systems. In the area of syntax, the paper focuses on the phenomenon of discontinuous constituents. A form of syntactic representation is defined, called discontinuous trees, which allows the constituent structure of sentences with discontinuous constituents to be represented without changing the word order in the sentence. A kind of phrase-structure gram.mar is defined which can generate such representations, and an on-line parsing algorithm is presented which parses sentences into these representations. In the area of semantics, the paper focuses on the effective resolution of ambiguity and vagueness, and on the on-line interpretation of anaphora. For dealing with ambiguous and vague expressions in an effective, on-line manner a cascaded model-theoretic approach is developed which makes use of intermediate semantic representations in a formal language that preserves some of the ambiguity and vagueness in natural language. For the interpretation of anaphora, an approach is outlined that has recently been suggested by Groenendijk and Stokhof, based on the use of dynamic logic. In the area of pragmatics, the paper focuses on the analysis of informationexchange dialogues as consisting of communicative actions. The notion function of a communicative action is defined in terms of the flow of information between speaker and addressee. It is argued that Groenendijk and Stokhof's dynamic approach to semantic interpretation can be elegantly combined with this`functional' approach to communicative action into in an integrated theory of utterance meaning. The resulting`dyna~nic interpretation theory' is outlined, which offers exciting perspectives for a full-fledged, on-line utterance interpretation process. (1) A process F is on-line if there is a function f such that for every input sequence C il, iz, .., ik~: F(G ii~iz,.-~ik~)-f(F(C ai~iz~..~tk-l1~Zk) Note that, if C il, iz, .., ik 1 is a sequence of inputs which forms part of a complete input sequence G il, izi .., i"~, according to this definition the processing of that part indeed takes place immediately, as it does not depend on later inputs.
Dialogue management in the Bell Labs communicator system
… International Conference on …, 2000
This paper describes a dialogue manager and its interaction with semantics and context tracking in a spoken dialogue system developed for general information retrieval and transaction applications. The dialogue system supports the following basic functionality: electronic form filling, database query, result navigation, attribute-value pair referencing, and value and reference resolution. General data structures and algorithms for representing and resolving ambiguity in a spoken dialogue system and a parsimonious parameterization for all application-dependent semantic and dialogue information are proposed. Dialogue management algorithms examine the semantics and dialogue state and adapt to the user's needs and task necessities. These algorithms are applied to a travel reservation application developed under the auspices of the DARPA Communicator project. The proposed algorithms are application-independent and facilitate ease of developing new spoken dialogue systems by changing only the semantics encoded in the prototype tree and the domain-dependent templates used by such components as the parser and the prompt generator.
On the Use of Context in Building Spoken Language Dialogue Systems for Large Tasks
Context is of crucial importance to language understanding in general and plays a central role in spoken language dialogue systems design. Context, however, is hard to define. In this paper context is viewed as denoting a collection of aspects or contextual elements each of which may be defined and analysed with respect to its specific contribution to dialogue understanding. Massive exploitation of context is essential in spoken language dialogue systems design for large tasks because the feasibility of such systems demands a high degree of control of the user-system dialogue. The paper discusses in detail how knowledge about contextual elements is used in system-directed dialogue design to achieve an optimal trade-off between technological feasibility and user acceptability and to enable controlled steps in the direction of mixed-initiative dialogue. The discussion is based on the design, implementation and test of system-directed dialogue for a spoken language dialogue system and ...