딥러닝 기반 한국어 개체명 인식의 평가와 오류 분석 연구Error Analysis and Evaluation of Deep-learning Based Korean Named Entity Recognition
- Authors
- 유현조; 송영숙; 김민수; 윤기현; 정유남
- Issue Date
- 2021
- Publisher
- 한국언어학회
- Keywords
- named entity recognition; Korean language; natural language processing; proper name; terminology
- Citation
- 언어, v.46, no.3, pp 803 - 828
- Pages
- 26
- Journal Title
- 언어
- Volume
- 46
- Number
- 3
- Start Page
- 803
- End Page
- 828
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/62795
- DOI
- 10.18855/lisoko.2021.46.3.010
- ISSN
- 1229-4039
2734-0481
- Abstract
- Named entity recognition is a natural language processing task that recognizes and classifies named entities in an unstructured text. The targets of NER are not limited to typical proper names for persons, locations and organizations, but also date, time and quantity expressions and can be further expanded to names of events, animals, plants, materials and other encyclopedic entities. A real-world NER system is also expected to be tuned to process domain-specific terminologies. In this study, the researchers built and tested a BERT based Korean NER system and proposed methods for evaluation and error analysis. The study trained the system with 140K word NER corpus and evaluated with 60K test. Error types are proposed to be categorized into four classes: detection, boundary, segmentation, and labelling. Error rates are found to vary greatly from 1% to 30% between entity labels, which are grouped into the most accurate time and quantity expressions, relatively accurate proper names, and highly erroneous terminologies. We expect that the error analysis will provide insights for finding a better way of data collection and post-processing correction.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - The Office of Research Affairs > Affiliated Research Institute > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.