Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers
With the accelerating development of science and technology, the academic papers being published in various fields are increasing rapidly. Academic papers specially in science and technology fields are a crucial media for researchers who develop new technologies by identifying knowledge regarding th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10003205/ |
| _version_ | 1797959601360994304 |
|---|---|
| author | Hyesoo Kong Hwamook Yoon Jaewook Seol Mihwan Hyun Hyejin Lee Soonyoung Kim Wonjun Choi |
| author_facet | Hyesoo Kong Hwamook Yoon Jaewook Seol Mihwan Hyun Hyejin Lee Soonyoung Kim Wonjun Choi |
| author_sort | Hyesoo Kong |
| collection | DOAJ |
| description | With the accelerating development of science and technology, the academic papers being published in various fields are increasing rapidly. Academic papers specially in science and technology fields are a crucial media for researchers who develop new technologies by identifying knowledge regarding the latest technological trends and conduct derivative studies in science and technology. Therefore, the continual collection of extensive academic papers, structuring of metadata, and construction of databases are significant tasks. However, research on automatic metadata extraction from Korean papers is not being actively conducted currently owing to insufficient Korean training data. We automatically constructed the largest labeled corpus in South Korea to date from 315,320 PDF papers belonging to 503 Korean academic journals and this labeled corpus can be used for training the models of automatic extraction for 12 metadata types from PDF papers. This labeled corpus is available at <uri>https://doi.org/10.23057/48</uri>. Moreover, we developed inspection process and guidelines for the automatically constructed data and performed a full inspection of the validation and testing data. The reliability of the inspected data was verified through the inter-annotator agreement measurement. Using our corpus, we trained and evaluated the BERT based transfer learning model to verify its reliability. Furthermore, we proposed new training methods that can improve the metadata extraction performance of Korean papers, and through these methods, we developed KorSciBERT-ME-J and KorSciBERT-ME-J+C models. The KorSciBERT-ME-J showed the highest performance with an F1 score of 99.36%, as well as robust performance in automatic metadata extraction from Korean academic papers in various formats. |
| first_indexed | 2024-04-11T00:35:01Z |
| format | Article |
| id | doaj.art-859f68b7f15c45ff830a8a75b6c301db |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T00:35:01Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-859f68b7f15c45ff830a8a75b6c301db2023-01-07T00:00:36ZengIEEEIEEE Access2169-35362023-01-011182583810.1109/ACCESS.2022.323322810003205Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic PapersHyesoo Kong0https://orcid.org/0000-0002-3742-7433Hwamook Yoon1Jaewook Seol2Mihwan Hyun3Hyejin Lee4Soonyoung Kim5Wonjun Choi6https://orcid.org/0000-0002-9711-0091Digital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaDigital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaDigital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaDigital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaDigital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaDigital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaDigital Curation Center, Korea Institute of Science and Technology Information, Daejeon, Republic of KoreaWith the accelerating development of science and technology, the academic papers being published in various fields are increasing rapidly. Academic papers specially in science and technology fields are a crucial media for researchers who develop new technologies by identifying knowledge regarding the latest technological trends and conduct derivative studies in science and technology. Therefore, the continual collection of extensive academic papers, structuring of metadata, and construction of databases are significant tasks. However, research on automatic metadata extraction from Korean papers is not being actively conducted currently owing to insufficient Korean training data. We automatically constructed the largest labeled corpus in South Korea to date from 315,320 PDF papers belonging to 503 Korean academic journals and this labeled corpus can be used for training the models of automatic extraction for 12 metadata types from PDF papers. This labeled corpus is available at <uri>https://doi.org/10.23057/48</uri>. Moreover, we developed inspection process and guidelines for the automatically constructed data and performed a full inspection of the validation and testing data. The reliability of the inspected data was verified through the inter-annotator agreement measurement. Using our corpus, we trained and evaluated the BERT based transfer learning model to verify its reliability. Furthermore, we proposed new training methods that can improve the metadata extraction performance of Korean papers, and through these methods, we developed KorSciBERT-ME-J and KorSciBERT-ME-J+C models. The KorSciBERT-ME-J showed the highest performance with an F1 score of 99.36%, as well as robust performance in automatic metadata extraction from Korean academic papers in various formats.https://ieeexplore.ieee.org/document/10003205/BERTcorpus constructionmetadata extractiontransfer learning |
| spellingShingle | Hyesoo Kong Hwamook Yoon Jaewook Seol Mihwan Hyun Hyejin Lee Soonyoung Kim Wonjun Choi Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers IEEE Access BERT corpus construction metadata extraction transfer learning |
| title | Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers |
| title_full | Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers |
| title_fullStr | Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers |
| title_full_unstemmed | Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers |
| title_short | Annotated Open Corpus Construction and BERT-Based Approach for Automatic Metadata Extraction From Korean Academic Papers |
| title_sort | annotated open corpus construction and bert based approach for automatic metadata extraction from korean academic papers |
| topic | BERT corpus construction metadata extraction transfer learning |
| url | https://ieeexplore.ieee.org/document/10003205/ |
| work_keys_str_mv | AT hyesookong annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers AT hwamookyoon annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers AT jaewookseol annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers AT mihwanhyun annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers AT hyejinlee annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers AT soonyoungkim annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers AT wonjunchoi annotatedopencorpusconstructionandbertbasedapproachforautomaticmetadataextractionfromkoreanacademicpapers |