ALBERT with Knowledge Graph Encoder Utilizing Semantic Similarity for Commonsense Question Answering

Recently, pre-trained language representation models such as bidirectional encoder representations from transformers (BERT) have been performing well in commonsense question answering (CSQA). However, there is a problem that the do not directly use explicit information of knowledge sources existing outside. To augment this, additional methods knowledge-aware graph network (KagNet) and multi-hop relation (MHGRN) proposed. In this study, we propose to latest model lite (ALBERT) with extraction technique. We also applying novel method, schema expansion recent models. Then, analyze effect graph-based techniques confirm effective some extent. Furthermore, show our proposed can achieve better performance than KagNet MHGRN CommonsenseQA dataset.