@inproceedings{tabatabaei-etal-2023-annotating,
title = "Annotating Research Infrastructure in Scientific Papers: An {NLP}-driven Approach",
author = "Tabatabaei, Seyed Amin and
Cheirmpos, Georgios and
Doornenbal, Marius and
Zigoni, Alberto and
Moore, Veronique and
Tsatsaronis, Georgios",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.44",
doi = "10.18653/v1/2023.acl-industry.44",
pages = "457--463",
abstract = "In this work, we present a natural language processing (NLP) pipeline for the identification, extraction and linking of Research Infrastructure (RI) used in scientific publications. Links between scientific equipment and publications where the equipment was used can support multiple use cases, such as evaluating the impact of RI investment, and supporting Open Science and research reproducibility. These links can also be used to establish a profile of the RI portfolio of each institution and associate each equipment with scientific output. The system we are describing here is already in production, and has been used to address real business use cases, some of which we discuss in this paper. The computational pipeline at the heart of the system comprises both supervised and unsupervised modules to detect the usage of research equipment by processing the full text of the articles. Additionally, we have created a knowledge graph of RI, which is utilized to annotate the articles with metadata. Finally, examples of the business value of the insights made possible by this NLP pipeline are illustrated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tabatabaei-etal-2023-annotating">
<titleInfo>
<title>Annotating Research Infrastructure in Scientific Papers: An NLP-driven Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Amin</namePart>
<namePart type="family">Tabatabaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Cheirmpos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Doornenbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Zigoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Moore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Tsatsaronis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we present a natural language processing (NLP) pipeline for the identification, extraction and linking of Research Infrastructure (RI) used in scientific publications. Links between scientific equipment and publications where the equipment was used can support multiple use cases, such as evaluating the impact of RI investment, and supporting Open Science and research reproducibility. These links can also be used to establish a profile of the RI portfolio of each institution and associate each equipment with scientific output. The system we are describing here is already in production, and has been used to address real business use cases, some of which we discuss in this paper. The computational pipeline at the heart of the system comprises both supervised and unsupervised modules to detect the usage of research equipment by processing the full text of the articles. Additionally, we have created a knowledge graph of RI, which is utilized to annotate the articles with metadata. Finally, examples of the business value of the insights made possible by this NLP pipeline are illustrated.</abstract>
<identifier type="citekey">tabatabaei-etal-2023-annotating</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.44</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.44</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>457</start>
<end>463</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating Research Infrastructure in Scientific Papers: An NLP-driven Approach
%A Tabatabaei, Seyed Amin
%A Cheirmpos, Georgios
%A Doornenbal, Marius
%A Zigoni, Alberto
%A Moore, Veronique
%A Tsatsaronis, Georgios
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tabatabaei-etal-2023-annotating
%X In this work, we present a natural language processing (NLP) pipeline for the identification, extraction and linking of Research Infrastructure (RI) used in scientific publications. Links between scientific equipment and publications where the equipment was used can support multiple use cases, such as evaluating the impact of RI investment, and supporting Open Science and research reproducibility. These links can also be used to establish a profile of the RI portfolio of each institution and associate each equipment with scientific output. The system we are describing here is already in production, and has been used to address real business use cases, some of which we discuss in this paper. The computational pipeline at the heart of the system comprises both supervised and unsupervised modules to detect the usage of research equipment by processing the full text of the articles. Additionally, we have created a knowledge graph of RI, which is utilized to annotate the articles with metadata. Finally, examples of the business value of the insights made possible by this NLP pipeline are illustrated.
%R 10.18653/v1/2023.acl-industry.44
%U https://aclanthology.org/2023.acl-industry.44
%U https://doi.org/10.18653/v1/2023.acl-industry.44
%P 457-463
Markdown (Informal)
[Annotating Research Infrastructure in Scientific Papers: An NLP-driven Approach](https://aclanthology.org/2023.acl-industry.44) (Tabatabaei et al., ACL 2023)
ACL
- Seyed Amin Tabatabaei, Georgios Cheirmpos, Marius Doornenbal, Alberto Zigoni, Veronique Moore, and Georgios Tsatsaronis. 2023. Annotating Research Infrastructure in Scientific Papers: An NLP-driven Approach. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 457–463, Toronto, Canada. Association for Computational Linguistics.