Comparison of the Evaluation Metrics for Neural Grammatical Error Correction With Overcorrection
- Authors
- Park, Chanjun; Yang, Yeongwook; Lee, Chanhee; Lim, Heuiseok
- Issue Date
- 2020
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Measurement; Task analysis; Machine learning; Error correction; Grammar; Commercialization; Benchmark testing; Grammar error correction; overcorrection; neural machine translation; copy mechanism; metric
- Citation
- IEEE ACCESS, v.8, pp.106264 - 106272
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE ACCESS
- Volume
- 8
- Start Page
- 106264
- End Page
- 106272
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/58981
- DOI
- 10.1109/ACCESS.2020.2998149
- ISSN
- 2169-3536
- Abstract
- Grammar error correction (GEC) refers to the proper correction of grammatical errors in a given sentence. Important factors to consider in GEC are not only the grammatical correction of the sentence, but also the recognition of a correct sentence in which no changes are required. However, GEC approaches in which deep learning recently started being used consider only the former aspect, which leads to overcorrection, whereby changes are made to a correct sentence unnecessarily. Because this bias is also reflected in performance metrics, conventional performance metrics consider only part of the important factors in GEC. This study proposes a new metric to consider both important aspects in GEC and to provide a new viewpoint for the GEC task. To the best of the authors knowledge, this study is the first to deal with comprehensively considering the correction performance and overcorrection problem in GEC. The experimental results demonstrate that the model performance ranking was reversed when evaluating the performance with the proposed metric compared to the General Language Understanding Evaluation benchmark , which only considers the correction performance. This indicates that the high performance of the correction does not result in less problems with the overcorrection and that the overcorrection problem should also be considered when evaluating the model performance. Moreover, we found that the copy mechanism helps to alleviate the problem of overcorrection.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Department of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.