论文标题
自然语言上的多步演绎推理：一项关于分布概括的实证研究
Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation
论文作者
论文摘要
将深度学习与象征性逻辑推理相结合，旨在利用这两个领域的成功，并引起越来越多的关注。灵感来自DeepLogic，这是一种端到端模型，该模型训练了逻辑程序的推理，我们介绍了Ima-Glove-GA，这是一种以自然语言表达的多步推理的迭代神经推理网络。在我们的模型中，推理是使用基于RNN的迭代记忆神经网络进行的，并具有门控注意机制。我们在三个数据集上评估了IMA-GLOVE-GA：副群，Conceptrules V1和Conceptrules V2。实验结果表明，与DeepLogic和其他RNN基线模型相比，具有封闭式注意力的深沟性可以实现更高的测试精度。当规则被淘汰时，我们的模型比罗伯塔·洛尔格（Roberta-Large）实现了更好的分布概括。此外，为了解决当前多步推理数据集中推理深度分布不平衡分布的问题，我们开发了Pararule-Plus，这是一个大型数据集，其中包含更多需要更深入推理步骤的示例。实验结果表明，添加Pararule-Plus可以在需要更深层次深度的示例中提高模型的性能。源代码和数据可从https://github.com/strong-ai-lab/multi-step-deductive-reasoning-over-natural语言获得。
Combining deep learning with symbolic logic reasoning aims to capitalize on the success of both fields and is drawing increasing attention. Inspired by DeepLogic, an end-to-end model trained to perform inference on logic programs, we introduce IMA-GloVe-GA, an iterative neural inference network for multi-step reasoning expressed in natural language. In our model, reasoning is performed using an iterative memory neural network based on RNN with a gated attention mechanism. We evaluate IMA-GloVe-GA on three datasets: PARARULES, CONCEPTRULES V1 and CONCEPTRULES V2. Experimental results show DeepLogic with gated attention can achieve higher test accuracy than DeepLogic and other RNN baseline models. Our model achieves better out-of-distribution generalisation than RoBERTa-Large when the rules have been shuffled. Furthermore, to address the issue of unbalanced distribution of reasoning depths in the current multi-step reasoning datasets, we develop PARARULE-Plus, a large dataset with more examples that require deeper reasoning steps. Experimental results show that the addition of PARARULE-Plus can increase the model's performance on examples requiring deeper reasoning depths. The source code and data are available at https://github.com/Strong-AI-Lab/Multi-Step-Deductive-Reasoning-Over-Natural-Language.
