arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.10012cs.AI
收藏

通过注入常识知识进行动作和状态变化的推理

Reasoning about Actions and State Changes by Injecting Commonsense Knowledge

Allen Institute for AI(艾伦人工智能研究所)

Niket Tandon, Bhavana Dalvi Mishra, Joel Grus, Wen-tau Yih, Antoine Bosselut, Peter Clark

摘要:

理解程序文本,例如,描述光合作用的段落,需要建模动作和它们产生的状态变化,以便可以回答关于不同时间点的实体的问题。尽管最近的几个系统在这项任务中取得了令人印象深刻的进展,但它们的预测可能在全球范围内不一致或极不可能。在本文中,我们展示了如何通过两种方式来改善段落上下文中的动作的预测效果:(1)通过结合全局的常识性约束(例如,不存在的实体不能被破坏),以及(2)通过用来自大规模语料库的偏好来偏置阅读(例如,树木很少移动)。与早期的方法不同,我们将问题视为神经结构预测任务,允许硬约束和软约束来引导模型远离不太可能的预测。我们发现,新模型在程序文本理解的基准数据集上的表现明显优于早期系统(相对增益为+8%),并且它还避免了早期系统做出的一些无意义的预测。

英文摘要:

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent systems have shown impressive progress in this task, their predictions can be globally inconsistent or highly improbable. In this paper, we show how the predicted effects of actions in the context of a paragraph can be improved in two ways: (1) by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and (2) by biasing reading with preferences from large-scale corpora (e.g., trees rarely move). Unlike earlier methods, we treat the problem as a neural structured prediction task, allowing hard and soft constraints to steer the model away from unlikely predictions. We show that the new model significantly outperforms earlier systems on a benchmark dataset for procedural text comprehension (+8% relative gain), and that it also avoids some of the nonsensical predictions that earlier systems make.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑