@inproceedings{sohrab-etal-2022-biomedcurator,
title = "{B}iomed{C}urator: Data Curation for Biomedical Literature",
author = "Sohrab, Mohammad Golam and
Duong, Khoa N.A. and
Masami, Ikeda and
Topi{\'c}, Goran and
Natsume-Kitatani, Yayoi and
Kuroda, Masakata and
Itoh, Mari Nogami and
Takamura, Hiroya",
editor = "Buntine, Wray and
Liakata, Maria",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations",
month = nov,
year = "2022",
address = "Taipei, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-demo.8",
pages = "63--71",
abstract = "We present BiomedCurator1, a web application that extracts the structured data from scientific articles in PubMed and ClinicalTrials.gov. BiomedCurator uses state-of-the-art natural language processing techniques to fill the fields pre-selected by domain experts in the relevant biomedical area. The BiomedCurator web application includes: text generation based model for relation extraction, entity detection and recognition, text classification model for extracting several fields, information retrieval from external knowledge base to retrieve IDs, and a pattern-based extraction approach that can extract several fields using regular expressions over the PubMed and ClinicalTrials.gov datasets. Evaluation results show that different approaches of BiomedCurator web application system are effective for automatic data curation in the biomedical domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sohrab-etal-2022-biomedcurator">
<titleInfo>
<title>BiomedCurator: Data Curation for Biomedical Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Golam</namePart>
<namePart type="family">Sohrab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khoa</namePart>
<namePart type="given">N.A.</namePart>
<namePart type="family">Duong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ikeda</namePart>
<namePart type="family">Masami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Topić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yayoi</namePart>
<namePart type="family">Natsume-Kitatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masakata</namePart>
<namePart type="family">Kuroda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mari</namePart>
<namePart type="given">Nogami</namePart>
<namePart type="family">Itoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wray</namePart>
<namePart type="family">Buntine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present BiomedCurator1, a web application that extracts the structured data from scientific articles in PubMed and ClinicalTrials.gov. BiomedCurator uses state-of-the-art natural language processing techniques to fill the fields pre-selected by domain experts in the relevant biomedical area. The BiomedCurator web application includes: text generation based model for relation extraction, entity detection and recognition, text classification model for extracting several fields, information retrieval from external knowledge base to retrieve IDs, and a pattern-based extraction approach that can extract several fields using regular expressions over the PubMed and ClinicalTrials.gov datasets. Evaluation results show that different approaches of BiomedCurator web application system are effective for automatic data curation in the biomedical domain.</abstract>
<identifier type="citekey">sohrab-etal-2022-biomedcurator</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-demo.8</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>63</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BiomedCurator: Data Curation for Biomedical Literature
%A Sohrab, Mohammad Golam
%A Duong, Khoa N.A.
%A Masami, Ikeda
%A Topić, Goran
%A Natsume-Kitatani, Yayoi
%A Kuroda, Masakata
%A Itoh, Mari Nogami
%A Takamura, Hiroya
%Y Buntine, Wray
%Y Liakata, Maria
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations
%D 2022
%8 November
%I Association for Computational Linguistics
%C Taipei, Taiwan
%F sohrab-etal-2022-biomedcurator
%X We present BiomedCurator1, a web application that extracts the structured data from scientific articles in PubMed and ClinicalTrials.gov. BiomedCurator uses state-of-the-art natural language processing techniques to fill the fields pre-selected by domain experts in the relevant biomedical area. The BiomedCurator web application includes: text generation based model for relation extraction, entity detection and recognition, text classification model for extracting several fields, information retrieval from external knowledge base to retrieve IDs, and a pattern-based extraction approach that can extract several fields using regular expressions over the PubMed and ClinicalTrials.gov datasets. Evaluation results show that different approaches of BiomedCurator web application system are effective for automatic data curation in the biomedical domain.
%U https://aclanthology.org/2022.aacl-demo.8
%P 63-71
Markdown (Informal)
[BiomedCurator: Data Curation for Biomedical Literature](https://aclanthology.org/2022.aacl-demo.8) (Sohrab et al., AACL-IJCNLP 2022)
ACL
- Mohammad Golam Sohrab, Khoa N.A. Duong, Ikeda Masami, Goran Topić, Yayoi Natsume-Kitatani, Masakata Kuroda, Mari Nogami Itoh, and Hiroya Takamura. 2022. BiomedCurator: Data Curation for Biomedical Literature. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations, pages 63–71, Taipei, Taiwan. Association for Computational Linguistics.