论文标题
社交常识性推理以及多头知识的关注
Social Commonsense Reasoning with Multi-Head Knowledge Attention
论文作者
论文摘要
社会常识性推理需要了解文本，有关社交事件及其务实含义的知识以及常识性推理技能。在这项工作中，我们提出了一个新颖的多头知识注意模型，该模型编码半结构化的常识性推理规则，并学会将它们纳入基于变压器的推理细胞中。我们在需要不同的推理技能的两个任务上评估模型的表现：绑架了自然语言推断和反事实不变性预测是一项新任务。我们表明，我们提出的模型改善了两项推理任务中强大的最新模型（即罗伯塔）的性能。据我们所知，值得注意的是，我们是第一个证明学习反事实推理的模型有助于预测绑架推理任务中最佳解释的模型的人。我们通过扰动知识并就模型的知识融合功能提供定性分析来验证模型推理能力的鲁棒性。
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.
