Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse
This work addresses a challenging symbol grounding task for AI systems that need to learn fine-grained visual concepts interactively, though it appears incremental in its approach.
The paper tackles the problem of discriminating among visually similar object classes within Interactive Task Learning (ITL) constraints, such as online, incremental, and few-shot learning, by exploiting the semantics of generic statements and their implicatures in discourse, resulting in more data-efficient grounding.
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).