论文标题
多步推断段落推理
Multi-Step Inference for Reasoning Over Paragraphs
论文作者
论文摘要
复杂的文本推理需要理解和链接在一起自由形式的谓词和逻辑连接剂。先前的工作在很大程度上试图象征性地或使用黑盒变压器进行此操作。我们提出了这两个极端之间的中间立场：一个组成模型，让人联想到可以执行链式逻辑推理的神经模块网络。该模型首先在上下文中找到相关句子，然后使用神经模块将它们链在一起。我们的模型在绳索上提供了显着的性能改进（与Reranker连接时，最高29 \％的相对误差减少），这是一个最近引入的复杂推理数据集。
Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground between these two extremes: a compositional model reminiscent of neural module networks that can perform chained logical reasoning. This model first finds relevant sentences in the context and then chains them together using neural modules. Our model gives significant performance improvements (up to 29\% relative error reduction when comfibined with a reranker) on ROPES, a recently introduced complex reasoning dataset.
