技術文書から物体のアフォーダンス事前知識を学習する試み
Towards Learning Object Affordance Priors from Technical Texts
非比喩的な技術文書から「XはYできる」という能力・様相の意味関係を抽出し、物体の受動的/能動的モダリティやアフォーダンスの事前知識を得る構想を提示した概念論文。
著者: Nicholas H. Kirk
分類: cs.LG, cs.AI, cs.CL, cs.RO
原文アブストラクト
Everyday activities performed by artificial assistants can potentially be executed naively and dangerously given their lack of common sense knowledge. This paper presents conceptual work towards obtaining prior knowledge on the usual modality (passive or active) of any given entity, and their affordance estimates, by extracting high-confidence ability modality semantic relations (X can Y relationship) from non-figurative texts, by analyzing co-occurrence of grammatical instances of subjects and verbs, and verbs and objects. The discussion includes an outline of the concept, potential and limitations, and possible feature and learning framework adoption.
