Social commonsense reasoning with multi-head knowledge attention
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 lear...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
November 2020
|
| In: |
Findings of the Association for Computational Linguistics - Findings of ACL: EMNLP 2020
Year: 2020, Pages: 2969-2980 |
| DOI: | 10.18653/v1/2020.findings-emnlp.267 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.18653/v1/2020.findings-emnlp.267 Verlag, lizenzpflichtig, Volltext: https://aclanthology.org/2020.findings-emnlp.267 
|
| Author Notes: | Debjit Paul, Anette Frank |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 10.07.2023 |
| Physical Description: | Online Resource |
| ISBN: | 9781952148903 |
| DOI: | 10.18653/v1/2020.findings-emnlp.267 |