Abstract:

As a critical task in the field of natural language processing， fact verification requires the ability to retrieve relevant evidences from large amount of plain text based on a given claim and use this evidence to reason and verify the claim. Previous studies usually use concatenation of evidence sentences or graph structure to represent the relationships among the evidences， but cannot represent the internal relevance among the evidences clearly. Therefore， a collaborative reasoning network model based on graph and text fusion — CNGT （Co-attention Network with Graph and Text fusion） was designed. The semantic fusion of evidence sentences was achieved by constructing evidence knowledge graph. Firstly， the evidential knowledge graph was constructed according to the evidence sentences， and the graph representation was learned by graph transformation encoder. Then， the BERT （Bidirectional Encoder Representations from Transformers） model was used to encode the claim and evidence sentences. Finally， the reasoning graph information and text features were fused effectively through the double-layer cooperative reasoning network. Experimental results show that the proposed model is better than the advanced model KGAT （Knowledge Graph Attention neTwork） on FEVER （Fact Extraction and VERification） dataset with Label Accuracy （LA） increased by 0.84 percentage points and FEVER score increased by 1.51 percentage points. It can be seen that the model pays more attention to the relationships among evidence sentences， demonstrating the interpretability of the model for the relationships among evidence sentences through the evidence graph.

Key words: fact verification, graph, graph transformation encoder, semantic fusion, cooperative reasoning network

摘要：

作为自然语言处理领域的一项关键任务，事实验证要求能够从大量的纯文本中根据给定的声明检索相关的证据，并使用这些证据推理验证声明。以往的研究通常利用证据句子拼接或图结构表示证据之间的关系，而不能清晰地表示各证据之间的内在关联。因此，设计一种基于图谱和文本融合的协同推理网络模型CNGT （Co-attention Network with Graph and Text fusion），以通过构建证据知识图谱和证据句子进行语义融合。首先，根据证据句子构建证据知识图谱，并利用图变换编码器学习图谱表示；其次，利用BERT （Bidirectional Encoder Representations from Transformers）模型对声明和证据编码；最后，通过双层协同推理网络有效地融合推理图谱信息和文本特征。实验结果表明，相较于先进模型KGAT （Knowledge Graph Attention neTwork），所提模型在FEVER （Fact Extraction and VERification）数据集上的标签准确率（LA）提高了0.84个百分点，FEVER得分提高了1.51个百分点。可见，所提模型更关注证据句子之间的关系，并且通过证据图谱展示出模型对证据句子关系的可解释性。

关键词: 事实验证, 图谱, 图变换编码器, 语义融合, 协同推理网络