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

TL;DR

This paper introduces OTTers, a new dataset and task for generating bridging utterances in open-domain dialogue to facilitate coherent topic transitions, and evaluates existing models on this task.

Contribution

The paper presents OTTers, a novel dataset for one-turn topic transition in dialogue, and adapts state-of-the-art models to this task for the first time.

Findings

Humans predominantly use bridging utterances for topic transitions.

Existing models can be adapted to generate bridging utterances.

The dataset enables evaluation of topic transition strategies.

Abstract

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.