Chinese Sentence Semantic Matching Based on Multi-Granularity Fusion Model

Zhang, Xu; Lu, Wenpeng; Zhang, Guoqiang; Li, Fangfang; Wang, Shoujin

Sentence semantic matching is the cornerstone of many natural language processing tasks, including Chinese language processing. It is well known that Chinese sentences with different polysemous words or word order may have totally different semantic meanings. Thus, to represent and match the sentence semantic meaning accurately, one challenge that must be solved is how to capture the semantic features from the multi-granularity perspective, e.g., characters and words. To address the above challenge, we propose a novel sentence semantic matching model which is based on the fusion of semantic features from character-granularity and word-granularity, respectively. Particularly, the multi-granularity fusion intends to extract more semantic features to better optimize the downstream sentence semantic matching. In addition, we propose the equilibrium cross-entropy, a novel loss function, by setting mean square error (MSE) as an equilibrium factor of cross-entropy. The experimental results conducted on Chinese open data set demonstrate that our proposed model combined with binary equilibrium cross-entropy loss function is superior to the existing state-of-the-art sentence semantic matching models.