The Theory and Use of Clarification Requests in Dialogue (original) (raw)

On the Means for Clarification in Dialogue

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. We then explain the implications of these results for a possible HPSG analysis of clarification requests and for an ongoing implementation of a clarification-capable dialogue system. 1

CLARIE: Handling Clarification Requests in a Dialogue System

Research on Language and Computation, 2006

This paper sets out a approach to clarification requests (CRs) general enough to cover all the major forms found in corpus data and specific enough to analyse the questions they ask about individual words and phrases. Its main features are a view of utterances as contextual abstracts with a radically abstracted semantic representation, and a view of CRs as standard utterances asking standard questions, but showing a particular kind of contextual dependence. It shows how it can be implemented computationally within a prototype text-based dialogue system, CLARIE, allowing it not only to generate CRs to clarify unknown reference and learn new words, but also to interpret and respond to user CRs, with both capabilities integrated within the standard dialogue processes and governed by empirical evidence.

CLARIE: the Clarication Engine

2004

This paper describes the CLARIE system, a prototype information-statebased text dialogue system designed to deal with many types of clarification requests (CRs) by using a highly contextualised semantic representation together with a suitable grounding process. This allows it to interpret and respond to user CRs, and generate its own CRs in order to clarify unknown reference and learn new words, with both integrated within the standard dialogue update processes.

A Dialogue System for Interpreting Fragments

2007

Introduction A major task for a dialogue system is the resolution of fragments. Basic examples include bare NP answers (1), where the bare NP John is resolved as the assertion John saw Mary, and sluicing (2), where the WhP who is interpreted as the question Which student saw John. (1) (2) (3) A: Who saw Mary? B: John A: A student saw John. B. Who? Either the antecedent or the fragment (or both) may be embedded (3). 1. A: Bill wonders who saw Mary. B: John. (John saw Mary) 2. A: Bill thinks a student saw John. B: Who? (Which student does Bill think saw John?) 3. A: Who saw Mary? B: John thinks Bill. (John thinks Bill saw Mary) 4. A: A student saw John. B: Bill wonders who. (Bill wonders which student saw John) Constructing a computational framework for interpreting such fragments in a principled and systematic way is important for the development of viable grammar-driven text understanding and dialogue management systems. 2 Theoretical Background 2.1 Ellipsis Resolution:

Processing Unknown Words in a Dialogue System

2002

This paper describes a method of processing unknown words in a HPSGbased dialogue system, with acquisition of lexical semantics via clarification questions answered by the user. Use of a highly contextualized semantic representation, together with an utterance-anaphoric view of clarification, allows the clarificational dialogue to be integrated within the grammar and governed by standard rules of conversation.

Semantics and Pragmatics in the ELTA Dialogue Project

This paper 1 describes work in progress concerning the semantic and pragmatic interpretation of utterances in human-computer natural language information dialogues, as developed in the ELTA project at Tilburg University. This project aims at developing and applying an integrated approach to semantic and pragmatic interpretation of dialogue utterances, where the application is sought in the form of a dialogue system capable of acting as a cooperative partner in an information dialogue. The ELTA project continues a line of work in language understanding, dialogue studies, and designing intelligent interactive systems. A salient feature of the ELTA approach is that it considers semantic (truthconditional) and pragmatic (speech act) interpretation to be fundamentally context-based; the resolution of ambiguity and vagueness, often considered to be the main task of natural language interpretation, is not approached as a goal in itself, but as something to be done only as demanded and to the extent required by the context of the application. In this paper we will be concerned with three issues in the study of dialogues: (1) underspeci cation in the semantic content of dialogue utterances; (2) the communicative functions of dialogue utterances as context-changing functions, and (3) the formal modelling of dialogue context.

Clarification, Ellipsis, and the Nature of Contextual Updates in Dialogue

Linguistics and Philosophy, 2004

The paper investigates an elliptical construction, Clarification Ellipsis, that occurs in dialogue. We suggest that this provides data that demonstrates that updates resulting from utterances cannot be defined in purely semantic terms, contrary to the prevailing assumptions of existing approaches to dynamic semantics. We offer a computationally oriented analysis of the resolution of ellipsis in certain cases of dialogue clarification. We show that this goes beyond standard techniques used in anaphora and ellipsis resolution and requires operations on highly structured, linguistically heterogeneous representations. We characterize these operations and the representations on which they operate. We offer an analysis couched in a version of Head-Driven Phrase Structure Grammar combined with a theory of information states (IS) in dialogue. We sketch an algorithm for the process of utterance integration in IS which leads to grounding or clarification. The account proposed here has direct applications to the theory of attitude reports, an issue which is explored briefly in the concluding remarks of the paper.

A Dialogue Specification System for Explanation

Synthese, 182(3), 2011, 349-374.

This paper builds a dialectical system of explanation with speech act rules that define the kinds of moves allowed, like requesting and offering an explanation. Pre and post- condition rules for the speech acts determine when a particular speech act can be put forward as a move in the dialogue, and what type of move or moves must follow it. A successful explanation has been achieved when there has been a transfer of understanding from the party giving the explanation to the party asking for it. The dialogue has an opening stage, an explanation stage and a closing stage. Whether a transfer of understanding has taken place is tested by a dialectical shift to an examination dialogue.

GUS, a frame-driven dialog system

Artificial Intelligence, 1977

GUS is the first of a series of experimental computer systems that we intend to construct as part of a program of research on language understanding. In large measure, these systems will fill the role of periodic progress reports, summarizing what we have learned, assessing the mutual coherence of the various lines of investigation we have been following, and saggestin# where more emphasis is needed in future work. GUS (Genial Understander System) is intended to engage a sympathetic and highly cooperative human in an English dialog, directed towards a specific goal within a very restricted domain of discourse. As a starting point, G US was restricted to the role of a travel agent in a conversation with a client who wants to make a simple return trip to a single city in California.