QRFA: A Data-Driven Model of Information-Seeking Dialogues

Svitlana Vakulenko, Kate Revoredo, Claudio Di Ciccio, Maarten de Rijke

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Understanding the structure of interaction processes helps us to improve information-seeking dialogue systems. Analyzing an interaction process boils down to discovering patterns in sequences of alternating utterances exchanged between a user and an agent. Process mining techniques have been successfully applied to analyze structured event logs, discovering the underlying process models or evaluating whether the observed behavior is in conformance with the known process. In this paper, we apply process mining techniques to discover patterns in conversational transcripts and extract a new model of information-seeking dialogues, QRFA, for Query, Request, Feedback, Answer. Our results are grounded in an empirical evaluation across multiple conversational datasets from different domains, which was never attempted before. We show that the QRFA model better reflects conversation flows observed in real information-seeking conversations than models proposed previously. Moreover, QRFA allows us to identify malfunctioning in dialogue system transcripts as deviations from the expected conversation flow described by the model via conformance analysis.
Original languageEnglish
Title of host publicationAdvances in Information Retrieval - 41st European Conference on Information Retrieval, ECIR 2019, Cologne, Germany, April 14-18, 2019, Proceedings, Part I
EditorsLeif Azzopardi, Benno Stein, Norbert Fuhr, Philipp Mayr, Claudia Hauff, Djoerd Hiemstra
PublisherSpringer
Pages541-557
Number of pages17
Volume11437
ISBN (Print)978-3-030-15711-1
DOIs
Publication statusPublished - Apr 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer

Keywords

  • Conversational search
  • Log analysis
  • Process mining

Fingerprint

Dive into the research topics of 'QRFA: A Data-Driven Model of Information-Seeking Dialogues'. Together they form a unique fingerprint.

Cite this