Follow-up utterances in QA dialogue

Boris van Schooten, Rieks op den Akker

Research output: Contribution to journalArticleAcademicpeer-review

23 Downloads (Pure)

Abstract

The processing of user follow-up utterances by a QA system is a topic which is still in its infant stages, but enjoys growing interest in the QA community. In this paper, we discuss the broader issues related to handling follow-up utterances in a real-life "information kiosk" setting. With help of a corpus of follow-up utterances, we lay out a general framework for QA dialogue, and propose a general-coverage classication of real user reactions, based on their function in the dialogue, and their relation to the context of previous utterances. We discuss a dialogue manager we have developed that handles the identied types of follow-up utterances. It uses existing NLP and IR techniques to handle follow-up questions, and generates appropriate dialogue reactions to handle non-follow-up questions. Our main conclusion is that a large part of follow-up utterances can be handled by a set of simple techniques, even though we found it is not easy to determine the exact context in which follow-up questions are to be understood.
Original languageEnglish
Pages (from-to)181-206
Number of pages26
JournalTraitement Automatique des Langues (TAL)
Volume46
Issue number3
Publication statusPublished - 29 Sep 2006

Fingerprint

Managers
dialogue
Processing
infant
coverage
manager
community
Utterance

Keywords

  • HMI-SLT: Speech and Language Technology
  • HMI-HF: Human Factors
  • METIS-248450
  • IR-63437
  • EWI-6938
  • follow-up questions
  • sentence rewriting
  • dialogue management
  • Question Answering

Cite this

van Schooten, B., & op den Akker, R. (2006). Follow-up utterances in QA dialogue. Traitement Automatique des Langues (TAL), 46(3), 181-206.
van Schooten, Boris ; op den Akker, Rieks. / Follow-up utterances in QA dialogue. In: Traitement Automatique des Langues (TAL). 2006 ; Vol. 46, No. 3. pp. 181-206.
@article{c5cb069caba941f9a04fa028f453a94a,
title = "Follow-up utterances in QA dialogue",
abstract = "The processing of user follow-up utterances by a QA system is a topic which is still in its infant stages, but enjoys growing interest in the QA community. In this paper, we discuss the broader issues related to handling follow-up utterances in a real-life {"}information kiosk{"} setting. With help of a corpus of follow-up utterances, we lay out a general framework for QA dialogue, and propose a general-coverage classication of real user reactions, based on their function in the dialogue, and their relation to the context of previous utterances. We discuss a dialogue manager we have developed that handles the identied types of follow-up utterances. It uses existing NLP and IR techniques to handle follow-up questions, and generates appropriate dialogue reactions to handle non-follow-up questions. Our main conclusion is that a large part of follow-up utterances can be handled by a set of simple techniques, even though we found it is not easy to determine the exact context in which follow-up questions are to be understood.",
keywords = "HMI-SLT: Speech and Language Technology, HMI-HF: Human Factors, METIS-248450, IR-63437, EWI-6938, follow-up questions, sentence rewriting, dialogue management, Question Answering",
author = "{van Schooten}, Boris and {op den Akker}, Rieks",
year = "2006",
month = "9",
day = "29",
language = "English",
volume = "46",
pages = "181--206",
journal = "Traitement Automatique des Langues (TAL)",
issn = "1248-9433",
publisher = "Association pour le Traitement Automatique des Langues (ATALA)",
number = "3",

}

van Schooten, B & op den Akker, R 2006, 'Follow-up utterances in QA dialogue' Traitement Automatique des Langues (TAL), vol. 46, no. 3, pp. 181-206.

Follow-up utterances in QA dialogue. / van Schooten, Boris; op den Akker, Rieks.

In: Traitement Automatique des Langues (TAL), Vol. 46, No. 3, 29.09.2006, p. 181-206.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Follow-up utterances in QA dialogue

AU - van Schooten, Boris

AU - op den Akker, Rieks

PY - 2006/9/29

Y1 - 2006/9/29

N2 - The processing of user follow-up utterances by a QA system is a topic which is still in its infant stages, but enjoys growing interest in the QA community. In this paper, we discuss the broader issues related to handling follow-up utterances in a real-life "information kiosk" setting. With help of a corpus of follow-up utterances, we lay out a general framework for QA dialogue, and propose a general-coverage classication of real user reactions, based on their function in the dialogue, and their relation to the context of previous utterances. We discuss a dialogue manager we have developed that handles the identied types of follow-up utterances. It uses existing NLP and IR techniques to handle follow-up questions, and generates appropriate dialogue reactions to handle non-follow-up questions. Our main conclusion is that a large part of follow-up utterances can be handled by a set of simple techniques, even though we found it is not easy to determine the exact context in which follow-up questions are to be understood.

AB - The processing of user follow-up utterances by a QA system is a topic which is still in its infant stages, but enjoys growing interest in the QA community. In this paper, we discuss the broader issues related to handling follow-up utterances in a real-life "information kiosk" setting. With help of a corpus of follow-up utterances, we lay out a general framework for QA dialogue, and propose a general-coverage classication of real user reactions, based on their function in the dialogue, and their relation to the context of previous utterances. We discuss a dialogue manager we have developed that handles the identied types of follow-up utterances. It uses existing NLP and IR techniques to handle follow-up questions, and generates appropriate dialogue reactions to handle non-follow-up questions. Our main conclusion is that a large part of follow-up utterances can be handled by a set of simple techniques, even though we found it is not easy to determine the exact context in which follow-up questions are to be understood.

KW - HMI-SLT: Speech and Language Technology

KW - HMI-HF: Human Factors

KW - METIS-248450

KW - IR-63437

KW - EWI-6938

KW - follow-up questions

KW - sentence rewriting

KW - dialogue management

KW - Question Answering

M3 - Article

VL - 46

SP - 181

EP - 206

JO - Traitement Automatique des Langues (TAL)

JF - Traitement Automatique des Langues (TAL)

SN - 1248-9433

IS - 3

ER -

van Schooten B, op den Akker R. Follow-up utterances in QA dialogue. Traitement Automatique des Langues (TAL). 2006 Sep 29;46(3):181-206.