QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec
Abstract
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. Here we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph-based message passing. We evaluate QA-GNN on the CommonsenseQA and OpenBookQA datasets, and show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.
BibTeX
@inproceedings{yasunaga-etal-2021-qa,
title = "{QA}-{GNN}: Reasoning with Language Models and Knowledge Graphs for Question Answering",
author = "Yasunaga, Michihiro and
Ren, Hongyu and
Bosselut, Antoine and
Liang, Percy and
Leskovec, Jure",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.45/",
doi = "10.18653/v1/2021.naacl-main.45",
pages = "535--546"
}