Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering

TL;DR

This paper introduces a semantic-driven, hierarchical knowledge injection framework for open-domain commonsense question answering, effectively filtering and fusing relevant knowledge to improve accuracy.

Contribution

It proposes a novel coarse-to-careful knowledge filtering and fusion method that leverages semantic cues to enhance commonsense QA performance.

Findings

Improved accuracy on CommonsenseQA dataset.

Effective filtering of noisy knowledge.

Hierarchical knowledge fusion enhances reasoning.

Abstract

It is prevalent to utilize external knowledge to help machine answer questions that need background commonsense, which faces a problem that unlimited knowledge will transmit noisy and misleading information. Towards the issue of introducing related knowledge, we propose a semantic-driven knowledge-aware QA framework, which controls the knowledge injection in a coarse-to-careful fashion. We devise a tailoring strategy to filter extracted knowledge under monitoring of the coarse semantic of question on the knowledge extraction stage. And we develop a semantic-aware knowledge fetching module that engages structural knowledge information and fuses proper knowledge according to the careful semantic of questions in a hierarchical way. Experiments demonstrate that the proposed approach promotes the performance on the CommonsenseQA dataset comparing with strong baselines.