arXiv Analytics

Sign in

arXiv:2105.13710 [cs.CL]AbstractReferencesReviewsResources

OTTers: One-turn Topic Transitions for Open-Domain Dialogue

Karin Sevegnani, David M. Howcroft, Ioannis Konstas, Verena Rieser

Published 2021-05-28Version 1

Mixed initiative in open-domain dialogue requires a system to pro-actively introduce new topics. The one-turn topic transition task explores how a system connects two topics in a cooperative and coherent manner. The goal of the task is to generate a "bridging" utterance connecting the new topic to the topic of the previous conversation turn. We are especially interested in commonsense explanations of how a new topic relates to what has been mentioned before. We first collect a new dataset of human one-turn topic transitions, which we call OTTers. We then explore different strategies used by humans when asked to complete such a task, and notice that the use of a bridging utterance to connect the two topics is the approach used the most. We finally show how existing state-of-the-art text generation models can be adapted to this task and examine the performance of these baselines on different splits of the OTTers data.

Related articles: Most relevant | Search more
arXiv:2209.07697 [cs.CL] (Published 2022-09-16)
Selecting Stickers in Open-Domain Dialogue through Multitask Learning
arXiv:2109.04137 [cs.CL] (Published 2021-09-09)
Fusing task-oriented and open-domain dialogues in conversational agents
arXiv:2205.06262 [cs.CL] (Published 2022-05-12)
FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue
Alon Albalak et al.