Knowledge Adaptive Neural Network for Natural Language Inference

Natural language inference (NLI) has received widespread attention in recent years due to its contribution to various natural language processing tasks, such as question answering, abstract text summarization, and video caption. Most existing works focus on modeling the sentence interaction information, while the use of commonsense knowledge is not well studied for NLI. In this paper, we propose knowledge adaptive neural network (KANN) that adaptively incorporates commonsense knowledge at sentence encoding and inference stages. We first perform knowledge collection and representation to identify the relevant knowledge. Then we use a knowledge absorption gate to embed knowledge into neural network models. Experiments on two benchmark datasets, namely SNLI and MultiNLI for natural language inference, show the advantages of our proposed model. Furthermore, our model is comparable to if not better than the recent neural network based approaches on NLI.