基于图神经网络和语义知识的自然语言推理任务研究

自然语言推理任务的目的是推断两个句子之间的语义逻辑关系。该文通过模仿人类的推理过程构造模型,首先利用长短时记忆网络提取词的语境特征,模仿人类粗读句子的过程;然后依据外部语义知识,连接两个句子中有语义联系的词,构造一个以词为节点的语义图;接下来模仿人类比较两个句子的语义角色相似性的思维,用图卷积或图注意力神经网络聚合词在图中的空间特征;最后融合词的语境特征和语义图空间特征,进行推理分类。实验结果证明,基于图神经网络的模型能有效利用外部语义知识来提高自然语言推理的准确率。

Natural Language Inference Model Based on Graph Neural Network and Semantic Knowledge

Natural language inference is to infer the semantic logical relationship between two given sentences. This paper proposes an inference model to simulate human thinking. Firstly, the context features of sentences are extracted by BiLSTM (bidirectional long short-term memory), which imitates human beings to understand sentence meaning. Then, the semantic graph for every pair of sentences is constructed according to the external semantic knowledge. The spatial features of words are extracted by graph convolutional network or graph attention network, which simulates the thinking mode of analyzing the semantic role similarity of two sentences. Finally, the semantic relationship of two sentences is inferred by integrating the context features and the spatial features. Further analysis reveals that the semantic knowledge is better exploited by graph neural network in natural language inference task.