On the Use of Context in Building Spoken Language Dialogue Systems for Large Tasks (original) (raw)
Related papers
Contextual Elements in the Danish Dialogue System
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. The discussion is based on the design, implementation and test of system-directed dialogue for a spoken language dialogue system.
Context Management with Topics for Spoken Dialogue Systems
1998
The paper presents the Constructive Dialogue Model as a new approach t o formulate system goals in intelligent d ialogue systems. The departure point is in general communicative principles which constrain cooperative and coherent communication. Dialogue participants are engaged in a cooperative task whereby a model of the joint purpose is constructed. Contributions are planned as reactions to the changing context, and no dialogue grammar is needed. Also speech act classication is abandoned, in favour of contextual reasoning and rationality considerations.
We present an evaluation of a spoken language dialogue system with a module for the management of userrelated information, stored as user preferences and privileges. The flexibility of our dialogue management approach, based on Bayesian Networks (BN), together with a contextual information module, which performs different strategies for handling such information, allows us to include user information as a new level into the Context Manager hierarchy. We propose a set of objective and subjective metrics to measure the relevance of the different contextual information sources. The analysis of our evaluation scenarios shows that the relevance of the short-term information (i.e. the system status) remains pretty stable throughout the dialogue, whereas the dialogue history and the user profile (i.e. the middle-term and the long-term information, respectively) play a complementary role, evolving their usefulness as the dialogue evolves.
Context and Content in Dialogue Systems
The paper outlines our dialogue model which comprises utterance analysis, processing and generation in a DRT framework. We present and discuss in detail an example from the EMBASSI domain 1 .
Context Representation and Reasoning for Managing Spoken Dialogue
2000
In interactive systems, the ~dialogue manager’ isa central component, whose primary task is to decide what o do next in a dialogue. This decision i volves taking a variety ofkinds of context information nto account, with different logical properties, u ed in different types of reasoning, andtherefore with different demands onrepresentation. In this paper we discuss the representation of the context information needed to support intelligent dialogue management in interactive speech systems. We argue that simple types of context information should be represented in a way that optimally supports efficient simple forms of reasoning, while other types of context information require sophisticated logics for articulate representation and full-blown reasoning. Using different types of representation for different types of context information creates a problem in situations where a type of context information, that is adequately represented in a very simple form most of the time, exceptional...
A dedicated task-oriented dialogue theory in support of spoken language dialogue systems design
1994
This paper presents steps towards an incremental dialogue theory in support of functional design of successive generations of spoken language dialogue systems. Dialogue functionality theory departs from a simple task taxonomy and develops a systematic set of concepts or dialogue elements and implementation strategies important to dialogue management. Increasingly complex tasks require the introduction of an increasing number of dialogue elements to ensure acceptable user-system interaction.
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.
Knowledge-Combining Methodology for Dialogue Design in Spoken Language Systems
Genetic Resources and Crop Evolution, 2005
In this paper, we propose a strategy for designing dialogue managers in spoken dialogue systems for a restricted domain. This strategy combines several information sources intuition, observation and simulation, in order to maximize the adaptation within the system capability and the expectation of the user. These sources are combined by an iterative process consisting of five steps, where different dialogue alternatives are proposed and evaluated sequentially. The evaluation process includes different measures depending on the information required. Several measures are proposed and analyzed in each step. We also describe a user-modeling technique and an approach for designing the confirmation sub-dialogues based on recognition confidence measures. The knowledge-combining methodology is described and applied to a railway information system. In a subjective evaluation, users from the university gave the system a 3.9 score on a 5-point scale with an average call duration of 205 seconds. The employers of the railway company were more critical of the system. They gave it a score of 2.1 even though the system resolved more than half of the calls (57.8%) within an average call duration of three minutes (185 seconds).
Spoken language dialogue: From theory to practice
1999
A spoken language dialogue system is composed of many parts: speech recognition, speech synthesis, natural language understanding, dialogue manager, database, etc. Building a spoken language system for a new application requires in general a big effort for integrating all these parts, in addition to the effort required for designing, testing and tuning the dialogue behavior. This is especially true when complex dialogue tasks are built based on a mixed initiative paradigm. The approach suggested in this paper consists in shaping both the overall general architecture as well as the particular dialogue strategy as sequential decision processes. We discuss the concepts of stateful and stateless dialogue managers and we introduce a scripting language, DMD, which supports both. Finally we conclude with the description of the dialogue manager implemented for the DARPA Communicator multi leg travel task.