Answer Span Correction in Machine Reading Comprehension

Revanth Gangi Reddy, Md Arafat Sultan, Efsun Sarioglu Kayi, Rong Zhang, Vittorio Castelli, Avi Sil


Abstract
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.
Anthology ID:
2020.findings-emnlp.226
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2496–2501
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.226
DOI:
10.18653/v1/2020.findings-emnlp.226
Bibkey:
Cite (ACL):
Revanth Gangi Reddy, Md Arafat Sultan, Efsun Sarioglu Kayi, Rong Zhang, Vittorio Castelli, and Avi Sil. 2020. Answer Span Correction in Machine Reading Comprehension. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2496–2501, Online. Association for Computational Linguistics.
Cite (Informal):
Answer Span Correction in Machine Reading Comprehension (Gangi Reddy et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.226.pdf
Data
MLQANatural QuestionsSQuAD