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

TL;DR

This paper enhances ALBERT with a knowledge graph encoder and schema graph expansion to improve commonsense question answering, demonstrating superior performance over existing models like KagNet and MHGRN.

Contribution

It introduces a novel schema graph expansion method and integrates knowledge graph information into ALBERT for better commonsense reasoning.

Findings

Schema graph expansion improves model performance.

Knowledge graph integration enhances commonsense understanding.

Proposed model outperforms KagNet and MHGRN on CommonsenseQA.

Abstract

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