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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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).
Original languageEnglish
Title of host publicationProceedings of the 15th International Conference on Computational Semantics (IWCS)
PublisherAssociation for Computational Linguistics
Pages318–331
Number of pages14
ISBN (Print)9781959429746
Publication statusPublished - 20 Jun 2023
Event15th International Conference on Computational Semantics - Nancy, France
Duration: 20 Jun 202323 Jun 2023
Conference number: 15
https://iwcs2023.loria.fr/

Conference

Conference15th International Conference on Computational Semantics
Abbreviated titleIWCS 2023
Country/TerritoryFrance
CityNancy
Period20/06/2323/06/23
Internet address

Fingerprint

Dive into the research topics of 'Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse'. Together they form a unique fingerprint.

Cite this