Asking More Informative Questions for Grounded Retrieval

Sedrick Keh, Justin Chiu, Daniel Fried


Abstract
When a model is trying to gather information in an interactive setting, it benefits from asking informative questions. However, in the case of a grounded multi-turn image identification task, previous studies have been constrained to polar yes/no questions (White et al., 2021), limiting how much information the model can gain in a single turn. We present an approach that formulates more informative, open-ended questions. In doing so, we discover that off-the-shelf visual question answering (VQA) models often make presupposition errors, which standard information gain question selection methods fail to account for. To address this issue, we propose a method that can incorporate presupposition handling into both question selection and belief updates. Specifically, we use a two-stage process, where the model first filters out images which are irrelevant to a given question, then updates its beliefs about which image the user intends. Through self-play and human evaluations, we show that our method is successful in asking informative open-ended questions, increasing accuracy over the past state-of-the-art by 14%, while resulting in 48% more efficient games in human evaluations.
Anthology ID:
2024.findings-naacl.276
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4429–4442
Language:
URL:
https://aclanthology.org/2024.findings-naacl.276
DOI:
Bibkey:
Cite (ACL):
Sedrick Keh, Justin Chiu, and Daniel Fried. 2024. Asking More Informative Questions for Grounded Retrieval. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4429–4442, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Asking More Informative Questions for Grounded Retrieval (Keh et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2024.findings-naacl.276.pdf
Copyright:
 2024.findings-naacl.276.copyright.pdf