[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Combining Structured and Unstructured Knowledge in an Interactive Search Dialogue System

Svetlana Stoyanchev, Suraj Pandey, Simon Keizer, Norbert Braunschweiler, Rama Sanand Doddipatla


Abstract
Users of interactive search dialogue systems specify their preferences with natural language utterances. However, a schema-driven system is limited to handling the preferences that correspond to the predefined database content. In this work, we present a methodology for extending a schema-driven interactive search dialogue system with the ability to handle unconstrained user preferences. Using unsupervised semantic similarity metrics and the text snippets associated with the search items, the system identifies suitable items for the user’s unconstrained natural language query. In crowd-sourced evaluation, the users chat with our extended restaurant search system. Based on objective metrics and subjective user ratings, we demonstrate the feasibility of using an unsupervised low latency approach to extend a schema-driven search dialogue system to handle unconstrained user preferences.
Anthology ID:
2022.sigdial-1.50
Volume:
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2022
Address:
Edinburgh, UK
Editors:
Oliver Lemon, Dilek Hakkani-Tur, Junyi Jessy Li, Arash Ashrafzadeh, Daniel Hernández Garcia, Malihe Alikhani, David Vandyke, Ondřej Dušek
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
531–540
Language:
URL:
https://aclanthology.org/2022.sigdial-1.50
DOI:
10.18653/v1/2022.sigdial-1.50
Bibkey:
Cite (ACL):
Svetlana Stoyanchev, Suraj Pandey, Simon Keizer, Norbert Braunschweiler, and Rama Sanand Doddipatla. 2022. Combining Structured and Unstructured Knowledge in an Interactive Search Dialogue System. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 531–540, Edinburgh, UK. Association for Computational Linguistics.
Cite (Informal):
Combining Structured and Unstructured Knowledge in an Interactive Search Dialogue System (Stoyanchev et al., SIGDIAL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigdial-1.50.pdf
Video:
 https://youtu.be/4f2urztZCdQ
Data
SGDSNLI