Chinese Sentences Similarity via Cross-Attention Based Siamese Network

2021/04/18 by Zhen Wang, Wang, Zhen, Xiangxie Zhang +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2104.08787

openalex publication_date 2021/04/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages. In this paper, we proposed a Cross-Attention Siamese Network (CATsNet) to carry out the task of learning the semantic meanings of Chinese sentences and comparing the similarity between two sentences. This novel model is capable of catching non-local features. Additionally, we also tried to apply the long short-term memory (LSTM) network in the model to improve its performance. The experiments were conducted on the LCQMC dataset and the results showed that our model could achieve a higher accuracy than previous work.

Citations

• Predicting the Semantic Textual Similarity with Siamese CNN and LSTM

Related

• Predicting the Semantic Textual Similarity with Siamese CNN and LSTM
• Siamese Networks for Semantic Pattern Similarity
• Learning Joint Multilingual Sentence Representations with Neural Machine Translation
• Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation
• A Distribution-Based Threshold for Determining Sentence Similarity