Jointly Considering Siamese Network and MatchPyramid Network for Text Semantic Matching
Zhoulin Tang, Jian Li · IOP Conference Series Materials Science and Engineering · 2019
When users ask questions in the Q&A website, the Q&A website often recommends similar questions to users. In order to improve the accuracy of recommendation, we propose a new text matching model: a text matching model based on Siamese semantic network and MatchPyramid model. Specifically, the algorithm combines the advanced features of Siamese semantic network with MatchPyramid model, and use these advanced features for classification. We compare our proposed model with several other models on the dataset provided by Quora and Alibaba. The results show that our proposed model performs better than other models.