A semantics-aware approach for multilingual natural language inference

Phuong Le-Hong, Erik Cambria

Abstract: This paper introduces a semantics-aware approach to natural language inference which allows neural network models to perform better on natural language inference benchmarks. We propose to incorporate explicit lexical and concept-level semantics from knowledge bases to improve inference accuracy. We conduct an extensive evaluation of four models using different sentence encoders, including continuous bag-of-words, convolutional neural network, recurrent neural network, and the transformer model. Experimental results demonstrate that semantics-aware neural models give better accuracy than those without semantics information. On average of the three strong models, our semantic-aware approach improves natural language inference in different languages.