Sentence Representation Method Based on Multi-Layer Semantic Network

With the development of artificial intelligence, more and people hope that computers can understand human language through natural technology, learn to think like beings, finally replace beings complete highly difficult tasks with cognitive ability. As key technology understanding, sentence representation reasoning mainly focuses on method model. Although performance has been improved, there are still some problems such as incomplete semantic expression, lack depth model, interpretability process. In this paper, a multi-layer network is designed for representation. The multi-attention mechanism obtains information different levels sentence. word order also integrated by adding relative position mask between words reduce uncertainty caused order. Finally, verified task text implication recognition emotion classification. experimental results show promote representation’s accuracy comprehensiveness.