Social commonsense reasoning with multi-head knowledge attention

• Verfasst von: Paul, Debjit [VerfasserIn]
• Verfasst von: Frank, Anette [VerfasserIn]
• Titel: Social commonsense reasoning with multi-head knowledge attention
• Verf.angabe: Debjit Paul, Anette Frank
• E-Jahr: 2020
• Jahr: November 2020
• Umfang: 12 S.
• Fussnoten: Gesehen am 10.07.2023
• Titel Quelle: Enthalten in: Conference on Empirical Methods in Natural Language Processing (2020 : Online)Findings of the Association for Computational Linguistics - Findings of ACL: EMNLP 2020
• Ort Quelle: Stroudsburg, PA : Association for Computational Linguistics (ACL), 2020
• Jahr Quelle: 2020
• Band/Heft Quelle: (2020) vom: Nov., Seite 2969-2980
• ISBN Quelle: 978-1-952148-90-3
• DOI: doi:10.18653/v1/2020.findings-emnlp.267
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Forschungsdaten: Paul, Debjit: Source code, data and additional material for the thesis: "Social commonsense reasoning with structured knowledge in text"
• K10plus-PPN: 1852304472

Abstract

Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. In this work we propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell.We assess the model's performance on two tasks that require different reasoning skills: Abductive Natural Language Inference and Counterfactual Invariance Prediction as a new task. We show that our proposed model improves performance over strong state-of-the-art models (i.e., RoBERTa) across both reasoning tasks. Notably we are, to the best of our knowledge, the first to demonstrate that a model that learns to perform counterfactual reasoning helps predicting the best explanation in an abductive reasoning task. We validate the robustness of the model's reasoning capabilities by perturbing the knowledge and provide qualitative analysis on the model's knowledge incorporation capabilities.