QAVSA: Question Answering using Vector Symbolic Algebras

ACL 2024 9th Workshop on Representation Learning for NLP, 2024

Ryan Laube, Chris Eliasmith

Abstract

With the advancement of large pretrained language models (PLMs), many question answering (QA) benchmarks have been developed in order to evaluate the reasoning capabilities of these models. Augmenting PLMs with external knowledge in the form of Knowledge Graphs (KGs) has been a popular method to improve their reasoning capabilities, and a common method to reason over KGs is to use Graph Neural Networks (GNNs). As an alternative to GNNs to augment PLMs, we propose a novel graph reasoning module using Vector Symbolic Algebra (VSA) graph representations and a k-layer MLP. We demonstrate that our VSA-based model performs as well as QA-GNN, a model combining a PLM and a GNN-module, on 3 multiple-choice question answering (MCQA) datasets. Our model has a simpler architecture than QA-GNN and also converges 39

Full text links

 External link

Conference Proceedings

Booktitle
ACL 2024 9th Workshop on Representation Learning for NLP

Cite

Plain text

BibTeX