论文标题
文本逻辑推理的话语感知的图形网络
Discourse-Aware Graph Networks for Textual Logical Reasoning
论文作者
论文摘要
文本逻辑推理，尤其是具有逻辑推理的问题的任务（QA）任务，需要意识到特定的逻辑结构。段落级别的逻辑关系代表了命题单位之间的必要或矛盾（例如，结论句子）。但是，由于当前的质量检查系统专注于基于实体的关系，因此无法探索此类结构。在这项工作中，我们提出了逻辑结构构成建模，以解决逻辑推理质量质量质量质量质量质量质量质量，并引入话语感知图形网络（DAGNS）。网络首先构建了利用在线话语连接和通用逻辑理论的逻辑图，然后通过端到端通过边缘 - 复杂机制发展逻辑关系并更新图形特征来学习逻辑表示。该管道应用于一般编码器，其基本功能与高级逻辑功能相结合，以进行答案预测。在三个文本逻辑推理数据集上进行的实验证明了dagns内置的逻辑结构的合理性以及学到的逻辑特征的有效性。此外，零射击转移结果显示了特征的通用性，对看不见的逻辑文本。
Textual logical reasoning, especially question-answering (QA) tasks with logical reasoning, requires awareness of particular logical structures. The passage-level logical relations represent entailment or contradiction between propositional units (e.g., a concluding sentence). However, such structures are unexplored as current QA systems focus on entity-based relations. In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs). The networks first construct logic graphs leveraging in-line discourse connectives and generic logic theories, then learn logic representations by end-to-end evolving the logic relations with an edge-reasoning mechanism and updating the graph features. This pipeline is applied to a general encoder, whose fundamental features are joined with the high-level logic features for answer prediction. Experiments on three textual logical reasoning datasets demonstrate the reasonability of the logical structures built in DAGNs and the effectiveness of the learned logic features. Moreover, zero-shot transfer results show the features' generality to unseen logical texts.
