Answer Span Correction in Machine Reading Comprehension
This work addresses a specific error tendency in MRC systems, offering an incremental improvement for researchers and practitioners in natural language processing.
The paper tackled the problem of partially correct answers in machine reading comprehension systems by proposing a post-processing correction method, which achieved statistically significant performance improvements over state-of-the-art systems in monolingual and multilingual evaluations.
Answer validation in machine reading comprehension (MRC) consists of verifying an extracted answer against an input context and question pair. Previous work has looked at re-assessing the "answerability" of the question given the extracted answer. Here we address a different problem: the tendency of existing MRC systems to produce partially correct answers when presented with answerable questions. We explore the nature of such errors and propose a post-processing correction method that yields statistically significant performance improvements over state-of-the-art MRC systems in both monolingual and multilingual evaluation.