Affiliation:
1. School of Software, XinJiang University, Urumqi, China
Abstract
This paper proposes a multi-feature spatial convolutional semantic matching model (BMCSA) based on BERT by enriching different feature spatial information of semantic features. BMCSA employs the BERT model to extract the semantic features of the text, then uses the two-dimensional convolutional network to extract different feature spatial information, and finally combines the Attention mechanism to capture the global feature spatial information. We use two different semantic matching data sets and a text inference data set to verify the effectiveness of the proposed model. Experimental results prove that BMCSA is better than the baseline model.
Subject
Artificial Intelligence,General Engineering,Statistics and Probability
Reference13 articles.
1. Zhang X. , Sun X. and Wang H. , Duplicate question identification by integrating framenet with neural networks, 32(1), 2018.
2. Sentence similarity based on semantic nets and corpus statistics;Li;IEEE Transactions on Knowledge and Data Engineering,2006
3. Intelligent question answering in restricted domains using deep learning and question pair matching;Cai;Ieee Access,2020
4. Finding structure in time;Elman;Cognitive Science,1990
5. Chen Q. , Hu Q. , Huang J.X. and He L. , Ca-rnn: using context-aligned recurrent neural networks for modeling sentence similarity, 32(1), 2018.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献