단어 시퀀스 레이블링과 후처리에 기반한 참고문헌 인용열 인식: 영어 및 독일어 데이터셋 대상 평가
Reference String Recognition based on Word Sequence Tagging and Post-processing: Evaluation with English and German Datasets
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Reference string recognition is to extract individual reference strings from a reference section of an academic article, which consists of a sequence of reference lines. This task has been attacked by heuristic-based, clustering-based, classification-based approaches, exploiting lexical and layout characteristics of reference lines. Most classification-based methods have used sequence labeling to assign labels to either a sequence of tokens within reference lines, or a sequence of reference lines. Unlike the previous token-level sequence labeling approach, this study attempts to assign different labels to the beginning, intermediate and terminating tokens of a reference string. After that, post-processing is applied to identify reference strings by predicting their beginning and/or terminating tokens. Experimental evaluation using English and German reference string recognition datasets shows that the proposed method obtains above 94% in the macro-averaged F1.
Abstract
Reference string recognition is to extract individual reference strings from a reference section of an academic article, which consists of a sequence of reference lines. This task has been attacked by heuristic-based, clustering-based, classification-based approaches, exploiting lexical and layout characteristics of reference lines. Most classification-based methods have used sequence labeling to assign labels to either a sequence of tokens within reference lines, or a sequence of reference lines. Unlike the previous token-level sequence labeling approach, this study attempts to assign different labels to the beginning, intermediate and terminating tokens of a reference string. After that, post-processing is applied to identify reference strings by predicting their beginning and/or terminating tokens. Experimental evaluation using English and German reference string recognition datasets shows that the proposed method obtains above 94% in the macro-averaged F1.
참고문헌 (16)
- I. Councill, "ParsCit: an Open-source CRF Reference String Parsing Package", Proceedings of the 6th International Conference on Language Resources and Evaluation(LREC) (2008)
- R. Kern, "Extraction of References Using Layout and Formatting Information from Scientific Articles", D-Lib Magazine, 19(9, pp.10) (2013), ~
- D. Tkaczyk, "New Methods for Metadata Extraction from Scientific Literature", PhD, pp.2015
- M. Korner, "Evaluating Reference String Extraction Using Line-Based Conditional Random Fields: A Case Study with German Language Publications", ADBIS 2017, 767, pp.137~145 (2017), CCIS
- J. Boyd, "Automatic Metadata Extraction The High Energy Physics Use Case, CERN-THESIS-2015-105", Master's, pp.2015
- "Pdfextract"[URL]
- Dominika Tkaczyk, "CERMINE: automatic extraction of structured metadata from scientific literature", International Journal on Document Analysis and Recognition (IJDAR), 18(4), pp.317~335 (2015), Springer Nature[DOI]
- P. Lopez, "GROBID: Combining Automatic Bibliographic Data Recognition and Term Extraction for Scholarship Publications", Proceedings of the 13th European Conference on Digital Libraries(ECDL), pp.473~474 (2009)
- A. Bhardwaj, "DeepBIBX: Deep Learning for Image Based Bibliographic Data Extraction", ICONIP 2017, pp.286~293 (2017)
- J. Lafferty, "Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data", Proceedings of the 18th International Conference on Machine Learning(ICML), pp.282~289 (2001)
- S. Bird, "The ACL Anthology Reference Corpus: A Reference Dataset for Bibliographic Research in Computational Linguistics", Proceedings of the 6th International Conference on Language Resources and Evaluation(LREC) (2008)
- S. Anzaroot, "A New Dataset for Fine-grained Citation Field Extraction", Proceedings of the ICML Workshop on Peer Reviewing and Publishing Models (2013)
- "Frequently Occurring Surnames from the 2010 Census"[URL]
- "CRF++: Yet Another CRF toolkit"[URL]
- [URL]