论文标题
基于桌子的事实验证与专家的自适应混合物
Table-based Fact Verification with Self-adaptive Mixture of Experts
论文作者
论文摘要
基于桌子的事实验证任务最近引起了广泛的关注，但仍然是一个非常具有挑战性的问题。它固有地要求对自然语言的信息推理，以及表上的不同数值和逻辑推理（例如，计数，最高级，比较）。考虑到，我们利用了专家的混合物，并在本文中提出了一种新方法：超适应性混合物网络（Samoe）。具体而言，我们已经开发了专家网络的混合物来识别和执行不同类型的推理 - 该网络由多个专家组成，每个专家都处理语义的特定部分以进行推理，而管理模块则用于确定每个专家网络对验证结果的贡献。开发了一种自适应方法来教授管理模块在没有外部知识的情况下更有效地结合不同专家的结果。实验结果表明，我们的框架在基准数据集TABFACT上达到了85.1％的精度，与以前的最新模型相当。我们希望我们的框架可以作为基于桌子验证的新基线。我们的代码可在https://github.com/thumlp/samoe上找到。
The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning -- the network is composed of multiple experts, each handling a specific part of the semantics for reasoning, whereas a management module is applied to decide the contribution of each expert network to the verification result. A self-adaptive method is developed to teach the management module combining results of different experts more efficiently without external knowledge. The experimental results illustrate that our framework achieves 85.1% accuracy on the benchmark dataset TabFact, comparable with the previous state-of-the-art models. We hope our framework can serve as a new baseline for table-based verification. Our code is available at https://github.com/THUMLP/SaMoE.
