Sentence Representation Method Based on Multi-Layer Semantic Network

• Published in: Applied sciences Vol. 11; no. 3; p. 1316
• Main Authors: Zheng, Wenfeng, Liu, Xiangjun, Yin, Lirong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.02.2021
• Subjects: Artificial intelligence; Cognition & reasoning; Cognitive ability; Cognitive tasks; Computers; Datasets; Language; multi-attention mechanism; multi-layer network; Multilayers; Natural language; Natural language processing; natural language reasoning; Neural networks; Reasoning; Representations; Semantics; sentence representation; Sentences; Social networks; Technology; Words (language)
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app11031316

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