Modeling Dialogue By Functional Sub Categorization
نویسندگان
چکیده
In this paper we present a dialogue model which has as its main goat to place in context the utterance generated by the speaker. The dialogue model considers that an intervention generates one or more ilocutive acts which are handled as flmctions. These functions subcategorize to or are subcategorized by other functions in the dialogue. The model uses an exchange schema with the purpose of expressing the different ftmctional subcategorizations. These schemas have properties close to the semantic forms of the verbs in a lexical-functional context. 1 INTRODUCTION In task-orientetl dialogues two speakers work in cooperation with the purpose of carrying out a plan. This type of interaction has a start and a development structured by the restrictions of space, thne, transaction object and role of the partieipanls. Carberry, 9211 have suggested that a coherent discourse consists of segments that are related to one another through some type of structuring relation. Our dialogue model tries to capture the goal-oriented nature of discourse, ideutifing the discourse structure by providing the details of a computational mechanism for recognizing the structural relationships. The model enables the incremental recognition of communicative goals using rewriting rules and functional equations. The grammar constructs the structural tree captnring the dialogical functions of the discourse using functional snbcategorization. The subcategorization process improves on previous approaches [Ferrary et al., 88; Bilage, 91; JOnsson, 911, increasing the expresive power of the traditional dialogue models by modeling the relationships among the communicative actions enabling the task of connecting discottr~. The different parts of the system have been implemented using a blackboard architecture. The process starts obUfining the f-slructure associated to the intervention making use of a lexical-functional grammar [Abaitua ct al., 9111. In a second phase the f-structure is refined providing the correct explanation, essentially it solves the verbal interpretation and obtains referential information. Then, the planner and/or the dialogue module suu't to work. In the remainder of this paper, we will present our dialogue model in a top-down manner. Firstly, we show the exchange structure attoptexl and the subcategorization process using two samples. Then, we explain the retroactive and proactive nature of the interaction and we conclude by presenting two kinds of special interventions, the complex ~lll(l compound interventions. 2 EXCIIANGE STRUCTURE We assign to the constituents of the exchange level initiative and reactive ilocutive functions. These functions qualify ctmstituents which are in the same level of structuration. The initiative …
منابع مشابه
Sub-lexical Dialogue Act Classification in a Spoken Dialogue System Support for the Elderly with Cognitive Disabilities
This paper presents a dialogue act classification for a spoken dialogue system that delivers necessary information to elderly subjects with mild dementia. Lexical features have been shown to be effective for classification, but the automatic transcription of spontaneous speech demands expensive language modeling. Therefore, this paper proposes a classifier that does not require language modelin...
متن کاملToward a Unified Theory of Human-Agent Modeling: A Position Paper
Approaches to Human-Agent Modeling can broadly be categorized as the use of agents to emulate (1) the outcome and (2) the process of human behavior. The first category can be further sub-divided into emulating the outcomes produced by individual humans and by groups of humans. This position paper proposes this categorization as the core of a unified theory of human-modeling.
متن کاملModeling Lateral Communication in Holonic Multi Agent Systems
Agents, in a multi agent system, communicate with each other through the process of exchanging messages which is called dialogue. Multi agent organization is generally used to optimize agents’ communications. Holonic organization demonstrates a self-similar recursive and hierarchical structure in which each holon may include some other holons. In a holonic system, lateral communication occurs b...
متن کاملGenerating Feedback and Sequencing Moves in a Dialogue System
In current dialogue systems, user utterances are often verified by the system to make sure the system heard the user right. While this mechanism is useful and important in dialogue systems, it covers only a small part of the spectrum of interactive communication management (ICM) devices occuring in human-human dialogue. A view of the full range of ICM dialogue moves can be useful for suggesting...
متن کاملI-dialogue: Modeling Agent Conversation by Streams and Lazy Evaluation
This paper defines and exemplifies a new computational abstraction called i-dialogue which aims to model communicative situations such as those where an agent conducts multiple concurrent conversations with other agents. The i-dialogue abstraction is inspired both by the dialogue abstraction proposed by [17] and by the STROBE model [4]. Idialogue models conversations among processes by means of...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1994