Metraipolis › archive › dc_b24060eaae79
Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue — arXiv:2609.31130
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31130
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:04:07.437Z
- SHA-256 of the archived text
adbb820678e8a59ca877fae7cdffd7ed522e081cfd5408484fc192ff84d2f600- Stable URL of this page
https://metraipolis.com/documento/dc_b24060eaae79
How to cite
Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue — arXiv:2609.31130 — arXiv (en), https://arxiv.org/abs/2609.31130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b24060eaae79 (Metraipolis archive dc_b24060eaae79, sha256 adbb820678e8a59ca877fae7cdffd7ed522e081cfd5408484fc192ff84d2f600)
BibTeX
@misc{dcb24060eaae79,
title = {Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue — arXiv:2609.31130},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31130},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b24060eaae79; sha256 adbb820678e8a59ca877fae7cdffd7ed522e081cfd5408484fc192ff84d2f600},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.31130 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:38:49.459Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).