login
Home / Papers / QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question...

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

458 Citations2021
Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut
journal unavailable

This work proposes a new model, QA-GNN, which addresses the problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) through two key innovations: relevance scoring and joint reasoning.

Abstract

Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.