Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations

Building socialbots that can have deep, engaging open-domain conversations with humans is one of the grand challenges of artificial intelligence (AI). To this end, bots need to be able to leverage world knowledge spanning several domains effectively when conversing with humans who have their own wor...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-08
Main Authors: Gopalakrishnan, Karthik, Hedayatnia, Behnam, Chen, Qinlang, Gottardi, Anna, Kwatra, Sanjeev, Venkatesh, Anu, Raefer Gabriel, Hakkani-Tur, Dilek
Format: Article
Language:English
Subjects:
Coders
Conversational artificial intelligence
Datasets
Encoders-Decoders
Human performance
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Building socialbots that can have deep, engaging open-domain conversations with humans is one of the grand challenges of artificial intelligence (AI). To this end, bots need to be able to leverage world knowledge spanning several domains effectively when conversing with humans who have their own world knowledge. Existing knowledge-grounded conversation datasets are primarily stylized with explicit roles for conversation partners. These datasets also do not explore depth or breadth of topical coverage with transitions in conversations. We introduce Topical-Chat, a knowledge-grounded human-human conversation dataset where the underlying knowledge spans 8 broad topics and conversation partners don't have explicitly defined roles, to help further research in open-domain conversational AI. We also train several state-of-the-art encoder-decoder conversational models on Topical-Chat and perform automated and human evaluation for benchmarking.
ISSN:2331-8422