我们需要回答那个问题吗?自然对话中潜在问题的显著性与可回答性
Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue
- Université de Lorraine(洛林大学)
- CNRS(法国国家科学研究中心)
- Inria(法国国家信息与自动化研究所)
- LORIA(洛林计算机科学及其应用实验室)
- University of Gothenburg(哥德堡大学)
- CLASP(语言理论与计算语言学中心)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
本研究基于QUD框架,利用7,124个自动生成问题探究对话中问题显著性与可回答性的关系,发现二者存在弱正相关,且该效应弱于独白文本,表明对话结构更难预测。
AI中文摘要:
我们通过研究生成潜在问题的显著性是否预示其后续被解决,实证探究了自然对话中基于讨论问题(QUD)的建模。基于Wu等人(2024)的工作,我们构建了一个包含7,124个问题的数据集,这些问题从英国国家语料库的 utterances 和先前上下文中自动生成,并标注了显著性和可回答性。我们发现对话中显著性与可回答性之间存在稳健但较低的正相关,表明更显著的问题更可能被处理。然而,这种效应明显弱于独白文本,表明对话结构更难预测。我们进一步观察到,结构化互动中标注者之间的一致性比组织较松散的对话更强。
英文摘要:
We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential questions predicts their subsequent resolution. Building on Wu et al. (2024), we construct a dataset of 7,124 questions automatically generated from utterances and preceding context from the British National Corpus, and annotated for salience and answerability. We find a robust but low positive correlation between salience and answerability in dialogue, indicating that more salient questions are more likely to be addressed. However, this effect is markedly weaker than in monologic text, suggesting that conversational structure is less predictable. We further observe that structured interactions exhibit stronger alignment between annotators than less organised dialogues.