Towards human-like conversational search systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

Voice search is currently widely available on the majority of mobile devices via use of Virtual Personal Assistants. However, despite its general availability, the use of voice interaction remains sporadic and is limited to basic search tasks such as checking weather updates and looking up answers to factual queries. Present-day voice search systems struggle to use relevant contextual information to maintain conversational state, and lack conversational initiative needed to clarify user’s intent, which hampers their usability and prevents users from engaging in more complex interaction activities. This research investigates the potential of a hypothesised interactive information retrieval system with human-like conversational abilities. To this end, we propose a series of usability studies that involve a working prototype of a conversational system that uses real time speech synthesis. The proposed experiments seek to provide empirical evidence that enabling a voice search system with human-like conversational abilities can lead to increased likelihood of its adoption.
LanguageEnglish
Title of host publicationCHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval
Place of PublicationNew York
Pages348-350
Number of pages3
ISBN (Electronic)9781450349253
DOIs
Publication statusPublished - 11 Mar 2018

Fingerprint

Speech synthesis
Information retrieval systems
Mobile devices
Availability
Experiments

Keywords

  • conversational search
  • interactive voice interfaces
  • usability testing
  • information retrieval
  • human-computer interaction

Cite this

Dubiel, M. (2018). Towards human-like conversational search systems. In CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval (pp. 348-350). New York . https://doi.org/10.1145/3176349.3176360
Dubiel, Mateusz. / Towards human-like conversational search systems. CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New York , 2018. pp. 348-350
@inproceedings{4b4ac34595e14579a134b5b3e684faaf,
title = "Towards human-like conversational search systems",
abstract = "Voice search is currently widely available on the majority of mobile devices via use of Virtual Personal Assistants. However, despite its general availability, the use of voice interaction remains sporadic and is limited to basic search tasks such as checking weather updates and looking up answers to factual queries. Present-day voice search systems struggle to use relevant contextual information to maintain conversational state, and lack conversational initiative needed to clarify user’s intent, which hampers their usability and prevents users from engaging in more complex interaction activities. This research investigates the potential of a hypothesised interactive information retrieval system with human-like conversational abilities. To this end, we propose a series of usability studies that involve a working prototype of a conversational system that uses real time speech synthesis. The proposed experiments seek to provide empirical evidence that enabling a voice search system with human-like conversational abilities can lead to increased likelihood of its adoption.",
keywords = "conversational search, interactive voice interfaces, usability testing, information retrieval, human-computer interaction",
author = "Mateusz Dubiel",
year = "2018",
month = "3",
day = "11",
doi = "10.1145/3176349.3176360",
language = "English",
pages = "348--350",
booktitle = "CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval",

}

Dubiel, M 2018, Towards human-like conversational search systems. in CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New York , pp. 348-350. https://doi.org/10.1145/3176349.3176360

Towards human-like conversational search systems. / Dubiel, Mateusz.

CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New York , 2018. p. 348-350.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Towards human-like conversational search systems

AU - Dubiel, Mateusz

PY - 2018/3/11

Y1 - 2018/3/11

N2 - Voice search is currently widely available on the majority of mobile devices via use of Virtual Personal Assistants. However, despite its general availability, the use of voice interaction remains sporadic and is limited to basic search tasks such as checking weather updates and looking up answers to factual queries. Present-day voice search systems struggle to use relevant contextual information to maintain conversational state, and lack conversational initiative needed to clarify user’s intent, which hampers their usability and prevents users from engaging in more complex interaction activities. This research investigates the potential of a hypothesised interactive information retrieval system with human-like conversational abilities. To this end, we propose a series of usability studies that involve a working prototype of a conversational system that uses real time speech synthesis. The proposed experiments seek to provide empirical evidence that enabling a voice search system with human-like conversational abilities can lead to increased likelihood of its adoption.

AB - Voice search is currently widely available on the majority of mobile devices via use of Virtual Personal Assistants. However, despite its general availability, the use of voice interaction remains sporadic and is limited to basic search tasks such as checking weather updates and looking up answers to factual queries. Present-day voice search systems struggle to use relevant contextual information to maintain conversational state, and lack conversational initiative needed to clarify user’s intent, which hampers their usability and prevents users from engaging in more complex interaction activities. This research investigates the potential of a hypothesised interactive information retrieval system with human-like conversational abilities. To this end, we propose a series of usability studies that involve a working prototype of a conversational system that uses real time speech synthesis. The proposed experiments seek to provide empirical evidence that enabling a voice search system with human-like conversational abilities can lead to increased likelihood of its adoption.

KW - conversational search

KW - interactive voice interfaces

KW - usability testing

KW - information retrieval

KW - human-computer interaction

U2 - 10.1145/3176349.3176360

DO - 10.1145/3176349.3176360

M3 - Conference contribution book

SP - 348

EP - 350

BT - CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval

CY - New York

ER -

Dubiel M. Towards human-like conversational search systems. In CHIIR '18 Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New York . 2018. p. 348-350 https://doi.org/10.1145/3176349.3176360