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.
@article{arxiv.2011.03435,
title = {Answer Span Correction in Machine Reading Comprehension},
author = {Revanth Gangi Reddy and Md Arafat Sultan and Efsun Sarioglu Kayi and Rong Zhang and Vittorio Castelli and Avirup Sil},
journal= {arXiv preprint arXiv:2011.03435},
year = {2020}
}