Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering
This addresses the challenge of filtering relevant commonsense knowledge for question answering systems, though it appears incremental as it builds on existing knowledge-aware QA methods.
The paper tackles the problem of noisy external knowledge in open-domain commonsense question answering by proposing a semantic-driven framework that controls knowledge injection in a coarse-to-careful fashion, achieving improved performance on the CommonsenseQA dataset compared to strong baselines.
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.