OTTers: One-turn Topic Transitions for Open-Domain Dialogue
Karin Sevegnani, David M. Howcroft, Ioannis Konstas, Verena Rieser The Interaction Lab, MACS Heriot-Watt University Edinburgh, Scotland, UK {karin.sevegnani, i.konstas,
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 OTTers111https://github.com/karinseve/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.
中文速览
开放域对话系统在主动切换话题时，往往要么生硬跳转、要么毫无铺垫，严重影响对话体验。为此，研究者提出了"单轮话题过渡"（one-turn topic transition）任务，要求系统生成一句"桥接"话语，借助常识推理自然地把上一个话题引向新话题；他们还众包收集了名为 OTTers 的数据集，包含 4316 条人工撰写的过渡话语，并将每对话题锚定到知识图谱（ConceptNet/Wikidata）上的实体路径。分析发现，人类最常用的策略正是这种"桥接"式过渡，且过渡话语中引入的新实体与知识图谱路径上的实体高度吻合。在模型层面，将多跳推理模型（基于 Abductive NLG 微调的 GPT-2）与知识图谱推理模块结合，在实体路径预测和话语生成两个维度上均优于普通 GPT-2，这表明引入结构化常识知识能显著提升话题过渡的自然度与可解释性，为构建真正具备混合主导权的开放域对话系统提供了可行路径。
原文 arXiv:2105.13710;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2105.13710v1