The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents

Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston


Abstract
We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss topics and situations, and perceive and converse about images. By multi-tasking on such a broad large-scale set of data, we hope to both move towards and measure progress in producing a single unified agent that can perceive, reason and converse with humans in an open-domain setting. We show that such multi-tasking improves over a BERT pre-trained baseline, largely due to multi-tasking with very large dialogue datasets in a similar domain, and that the multi-tasking in general provides gains to both text and image-based tasks using several metrics in both the fine-tune and task transfer settings. We obtain state-of-the-art results on many of the tasks, providing a strong baseline for this challenge.
Anthology ID:
2020.acl-main.222
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2453–2470
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.222
DOI:
10.18653/v1/2020.acl-main.222
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.222.pdf
Video:
 http://slideslive.com/38928890