Reference Knowledgeable Network for Machine Reading Comprehension
This work provides an incremental improvement for researchers and practitioners in Machine Reading Comprehension by enhancing model performance through explicit knowledge integration.
The paper addresses multi-choice Machine Reading Comprehension (MRC) by proposing RekNet, a model that incorporates external knowledge to compensate for deficiencies in the provided passage. RekNet achieves consistent and remarkable performance improvements with observable statistical significance over strong baselines on RACE, DREAM, and Cosmos QA benchmarks.
Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of specific tasks or complex networks, without explicitly referring to relevant and credible external knowledge sources, which are supposed to greatly make up for the deficiency of the given passage. Thus we propose a novel reference-based knowledge enhancement model called Reference Knowledgeable Network (RekNet), which simulates human reading strategies to refine critical information from the passage and quote explicit knowledge in necessity. In detail, RekNet refines finegrained critical information and defines it as Reference Span, then quotes explicit knowledge quadruples by the co-occurrence information of Reference Span and candidates. The proposed RekNet is evaluated on three multi-choice MRC benchmarks: RACE, DREAM and Cosmos QA, obtaining consistent and remarkable performance improvement with observable statistical significance level over strong baselines. Our code is available at https://github.com/Yilin1111/RekNet.