• Journal of the Korean Society for information Management
• /
• v.40 no.2
• /
• pp.115-135
• /
• 2023

The purpose of this study is to assess the effectiveness of using deep learning language models to extract references automatically and create a reference database for research reports in an efficient manner. Unlike academic journals, research reports present difficulties in automatically extracting references due to variations in formatting across institutions. In this study, we addressed this issue by introducing the task of separating references from non-reference phrases, in addition to the commonly used metadata extraction task for reference extraction. The study employed datasets that included various types of references, such as those from research reports of a particular institution, academic journals, and a combination of academic journal references and non-reference texts. Two deep learning language models, namely RoBERTa+CRF and ChatGPT, were compared to evaluate their performance in automatic extraction. They were used to extract metadata, categorize data types, and separate original text. The research findings showed that the deep learning language models were highly effective, achieving maximum F1-scores of 95.41% for metadata extraction and 98.91% for categorization of data types and separation of the original text. These results provide valuable insights into the use of deep learning language models and different types of datasets for constructing reference databases for research reports including both reference and non-reference texts.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.3
• /
• pp.241-264
• /
• 2022

Bibliographic metadata can help researchers effectively utilize essential publications that they need and grasp academic trends of their own fields. With the manual creation of the metadata costly and time-consuming. it is nontrivial to effectively automatize the metadata construction using rule-based methods due to the immoderate variety of the article forms and styles according to publishers and academic societies. Therefore, this study proposes a two-step extraction process based on rules and deep neural networks for generating bibliographic metadata of scientific articlles to overcome the difficulties above. The extraction target areas in articles were identified by using a deep neural network-based model, and then the details in the areas were analyzed and sub-divided into relevant metadata elements. IThe proposed model also includes a model for generating reference summary information, which is able to separate the end of the text and the starting point of a reference, and to extract individual references by essential rule set, and to identify all the bibliographic items in each reference by a deep neural network. In addition, in order to confirm the possibility of a model that generates the bibliographic information of academic papers without pre- and post-processing, we conducted an in-depth comparative experiment with various settings and configurations. As a result of the experiment, the method proposed in this paper showed higher performance.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.461-464
• /
• 2018

최근 학술문헌이 급격하게 증가함에 따라, 학술문헌간의 연결성 및 메타데이터 추출 등의 핵심 자원으로서 활용할 수 있는 참고문헌에 대한 활용 연구가 진행되고 있다. 본 연구에서는 국내 학술지의 참고문헌이 가진 각 메타데이터를 자동적으로 인식하여 추출할 수 있는 참고문헌 메타데이터 인식에 대하여, 연속적 레이블링 방법론을 기반으로 접근한다. 심층학습 기술 중 연속적 레이블링에 우수한 성능을 보이고 있는 Bidirectional GRU-GRU CRF 모델을 기반으로 참고문헌 메타데이터 인식에 적용하였으며, 2010년 이후의 10종의 학술지내의 144,786건의 논문을 활용하여 추출한 169,668건의 참고문헌을 가공하여 실험하였다. 실험 결과, 실험집합에 대하여 F1 점수 97.21%의 우수한 성능을 보였다.

• Journal of the Korean Society for information Management
• /
• v.38 no.1
• /
• pp.221-242
• /
• 2021

This study applied reference metadata recognition using bidirectional GRU-CRF model based on pre-trained language model. The experimental group consists of 161,315 references extracted by 53,562 academic documents in PDF format collected from 40 journals published in 2018 based on rules. In order to construct an experiment set. This study was conducted to automatically extract the references from academic literature in PDF format. Through this study, the language model with the highest performance was identified, and additional experiments were conducted on the model to compare the recognition performance according to the size of the training set. Finally, the performance of each metadata was confirmed.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.188-190
• /
• 2012

인용 레코드 추출은 인용 색인 구축의 모든 프로세스 입력으로 사용되기 때문에 이후의 과정에 미칠 수 있는 부작용을 고려해서 최대한 정확한 정보가 추출되어야 한다. 본 논문에서는 수집한 논문의 참고문헌 영역을 인식하고 이를 참고문헌 영역 내의 특징들을 이용하여 인용 레코드를 추출하는 템플릿 기반 인용 레코드 추출을 제안한다. 제안된 추출 방법은 기존 방법보다 18% 성능이 증가했으며 전체 인용 레코드에 대한 추출성능은 0.98(F1)의 성능을 보인다. 이는 향후 논문 저장소에서 논문을 대상으로 영역 인식을 통한 정보 추출에 유용하게 활용될 수 있으리라 기대된다.

• Proceedings of the Korean Society for Information Management Conference
• /
• 1996.08a
• /
• pp.57-60
• /
• 1996

전문데이터베이스는 원문의 접근가능성과 전문탐색의 장점으로 인해 최근 급속하게 발전하고 있다. 그러나 이제까지 대부분의 전문데이터베이스는 문헌의 구조를 고려하지 않고 본문의 문자열에서 자동추출한 색인어를 대상으로 비통제탐색방법을 사용하여 왔으므로 효율적이고 다양한 검색방법을 적용하기 어려웠다. 본 연구에서는 SGML을 이용하여 문헌을 구조화하고 이를 이용한 색인시스템을 설계함으로써, 문헌구조를 이용한 다양한 검색이 가능하도록 하였다. 이를 위해 논문을 대상으로 하여 문헌의 구조를 분석하고, 주요 문헌요소인 초록, 목차, 본문, 참고문헌의 특성을 색인에 반영하였다. 색인시스템은 문헌요소를 태그와 텍스트데이터로 분석하여 색인하는 일차색인과, 일차색인에 의해 만들어진 문헌요소테이블과 내용데이터파일을 이용하여 주요 문헌요소를 색인한 이차색인으로 구성된다.

• Journal of Information Management
• /
• v.41 no.3
• /
• pp.155-173
• /
• 2010

With the advanced learning and the diversity of topics, researchers on each area keenly feel the need of precise and a quick discovery of required information at any time. This study presents a way of constructing the automatic mapping system that can compare and analyze duplicated data and that describes the result by building an effective reference extraction method and another way of correcting the wrong form of used Chinese characters with Traditional Korean Medicine dictionary. With this innovation, data duplication on references and Chinese characters errors can be fixed. Under the situation that a number of references of newly published papers that can continuously be extracted.

• Journal of Information Management
• /
• v.41 no.3
• /
• pp.191-209
• /
• 2010

A reference linking service that is connection of each other different information resource need to setup the reference database and to match identifier. CrossRef, PubMed and Web Of Science etc. the many overseas agencies developed reference linking service, that they used the automatic tools of Inera eXstyles, Parity Computings Reference Extractor etc. and setup in base DOI and PMID etc. Domestic the various agencies of KISTI(Korea Institute Science and Technology of Information), KRF(Korea Research Foundation) etc are construction reference database. But each research communities adopts a various reference bibliography writing format. As, the data base construction which is collect is confronting is many to being difficult. In this paper, We developed the Citation Matcher System. This system is automatic parsing the reference string to metadata and matching DOI, PMID and KOI as Identifier. It is improved the effectiveness of reference database setup.