Abstract
We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation. Inspired by previous work on planning-based summarisation, we present a model which instead of directly generating a question, sequentially predicts first a fact then a question. We evaluate our approach on 37k test dialogs adapted from the KGConv dataset and we show that, although more demanding in terms of inference, our approach performs on par with a standard model which solely generates a question while allowing for a detailed referenceless evaluation of the model behaviour in terms of relevance, factuality and pronominalisation.
Abstract (translated)
我们在知识本底的对话中探索问题生成,重点关注可解释性和评估。受到之前基于规划的摘要工作的启发,我们提出了一个模型,该模型在直接生成问题之前,先预测一个事实,然后是一个问题。我们在KGConv数据集上使用了37k个测试对话来评估我们的方法,我们证明了,尽管在推理方面更加具有挑战性,但我们的方法在相关性、事实性和名词化方面的行为与仅生成一个问题而允许对模型行为进行详细的有建设性的评估的标准模型相当。
URL
https://arxiv.org/abs/2404.07836