English

Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge

Computation and Language 2019-10-17 v1

Abstract

In this paper we present OSCAR (Ontology-based Semantic Composition Augmented Regularization), a method for injecting task-agnostic knowledge from an Ontology or knowledge graph into a neural network during pretraining. We evaluated the impact of including OSCAR when pretraining BERT with Wikipedia articles by measuring the performance when fine-tuning on two question answering tasks involving world knowledge and causal reasoning and one requiring domain (healthcare) knowledge and obtained 33:3%, 18:6%, and 4% improved accuracy compared to pretraining BERT without OSCAR and obtaining new state-of-the-art results on two of the tasks.

Keywords

Cite

@article{arxiv.1910.07429,
  title  = {Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge},
  author = {Travis R. Goodwin and Dina Demner-Fushman},
  journal= {arXiv preprint arXiv:1910.07429},
  year   = {2019}
}

Comments

6 pages, 5 figures, 2 tables

R2 v1 2026-06-23T11:45:35.797Z