Chinese Sentences Similarity via Cross-Attention Based Siamese Network
This work addresses sentence similarity for Chinese language processing, representing an incremental improvement with specific gains.
The paper tackled the problem of measuring Chinese sentence similarity by proposing a Cross-Attention Siamese Network (CATsNet) with LSTM integration, achieving higher accuracy on the LCQMC dataset compared to previous work.
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.