Table-based Fact Verification with Self-adaptive Mixture of Experts

TL;DR

This paper introduces SaMoE, a self-adaptive mixture-of-experts neural network for table-based fact verification, effectively recognizing diverse reasoning types and achieving state-of-the-art accuracy on the TabFact benchmark.

Contribution

The paper proposes a novel self-adaptive mixture-of-experts model that dynamically combines reasoning experts for improved fact verification over tables.

Findings

Achieves 85.1% accuracy on TabFact dataset.

Effective recognition and execution of various reasoning types.

Establishes a new baseline for table-based verification.

Abstract

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.