Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse

Jonghyuk Park, Alex Lascarides, Subramanian Ramamoorthy


Abstract
Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task—discriminating among object classes that look very similar—within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher’s generic statements (e.g., “Xs have attribute Z.”) and their implicatures in context (e.g., as an answer to “How are Xs and Ys different?”, one infers Y lacks attribute Z).
Anthology ID:
2023.iwcs-1.33
Volume:
Proceedings of the 15th International Conference on Computational Semantics
Month:
June
Year:
2023
Address:
Nancy, France
Editors:
Maxime Amblard, Ellen Breitholtz
Venue:
IWCS
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
318–331
Language:
URL:
https://aclanthology.org/2023.iwcs-1.33
DOI:
Bibkey:
Cite (ACL):
Jonghyuk Park, Alex Lascarides, and Subramanian Ramamoorthy. 2023. Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse. In Proceedings of the 15th International Conference on Computational Semantics, pages 318–331, Nancy, France. Association for Computational Linguistics.
Cite (Informal):
Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse (Park et al., IWCS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2023.iwcs-1.33.pdf