CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions
| Autor: | Tayfun Ates, M. Ateşoğlu, Çağatay Yiğit, Ilker Kesen, Mert Kobas, Erkut Erdem, Aykut Erdem, Tilbe Goksun, Deniz Yuret |
|---|---|
| Přispěvatelé: | Erdem, İbrahim Aykut (ORCID 0000-0002-6280-8422 & YÖK ID 20331), Göksun, Tilbe (ORCID 0000-0002-0190-7988 & YÖK ID 47278), Yüret, Deniz (ORCID 0000-0002-7039-0046 & YÖK ID 179996), Kesen, İlker, Kobaş, Mert, Erkut, Erdem, Ateş, Tayfun, Ateşoğlu, M. Şamil, Yiğit, Çağatay, Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI), Graduate School of Sciences and Engineering, College of Engineering, College of Social Sciences and Humanities, Department of Computer Engineering, Department of Psychology |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science Linguistics Artificial Intelligence (cs.AI) Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Vision and Pattern Recognition (cs.CV) Artificial intelligence Theory and methods Computer Science - Computer Vision and Pattern Recognition Computation and Language (cs.CL) |
| Zdroj: | Findings of the Association for Computational Linguistics |
| Popis: | Humans are able to perceive, understand and reason about causal events. Developing models with similar physical and causal understanding capabilities is a long-standing goal of artificial intelligence. As a step towards this direction, we introduce CRAFT1, a new video question answering dataset that requires causal reasoning about physical forces and object interactions. It contains 58K video and question pairs that are generated from 10K videos from 20 different virtual environments, containing various objects in motion that interact with each other and the scene. Two question categories in CRAFT include previously studied descriptive and counterfactual questions. Additionally, inspired by the Force Dynamics Theory in cognitive linguistics, we introduce a new causal question category that involves understanding the causal interactions between objects through notions like cause, enable, and prevent. Our results show that even though the questions in CRAFT are easy for humans, the tested baseline models, including existing state-of-the-art methods, do not yet deal with the challenges posed in our benchmark. CRAFT was supported in part by GEBIP 2018 Award of the Turkish Academy of Sciences to E. Erdem and T. Goksun, BAGEP 2021 Award of the Science Academy to A. Erdem, and AI Fellowship to Ilker Kesen provided by the KUIS AI Center. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|