@inproceedings{ahmad-etal-2024-forc4cl,
title = "{F}o{RC}4{CL}: A Fine-grained Field of Research Classification and Annotated Dataset of {NLP} Articles",
author = "Ahmad, Raia Abu and
Borisova, Ekaterina and
Rehm, Georg",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.651",
pages = "7389--7394",
abstract = "The steep increase in the number of scholarly publications has given rise to various digital repositories, libraries and knowledge graphs aimed to capture, manage, and preserve scientific data. Efficiently navigating such databases requires a system able to classify scholarly documents according to the respective research (sub-)field. However, not every digital repository possesses a relevant classification schema for categorising publications. For instance, one of the largest digital archives in Computational Linguistics (CL) and Natural Language Processing (NLP), the ACL Anthology, lacks a system for classifying papers into topics and sub-topics. This paper addresses this gap by constructing a corpus of 1,500 ACL Anthology publications annotated with their main contributions using a novel hierarchical taxonomy of core CL/NLP topics and sub-topics. The corpus is used in a shared task with the goal of classifying CL/NLP papers into their respective sub-topics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmad-etal-2024-forc4cl">
<titleInfo>
<title>FoRC4CL: A Fine-grained Field of Research Classification and Annotated Dataset of NLP Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raia</namePart>
<namePart type="given">Abu</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Borisova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The steep increase in the number of scholarly publications has given rise to various digital repositories, libraries and knowledge graphs aimed to capture, manage, and preserve scientific data. Efficiently navigating such databases requires a system able to classify scholarly documents according to the respective research (sub-)field. However, not every digital repository possesses a relevant classification schema for categorising publications. For instance, one of the largest digital archives in Computational Linguistics (CL) and Natural Language Processing (NLP), the ACL Anthology, lacks a system for classifying papers into topics and sub-topics. This paper addresses this gap by constructing a corpus of 1,500 ACL Anthology publications annotated with their main contributions using a novel hierarchical taxonomy of core CL/NLP topics and sub-topics. The corpus is used in a shared task with the goal of classifying CL/NLP papers into their respective sub-topics.</abstract>
<identifier type="citekey">ahmad-etal-2024-forc4cl</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.651</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7389</start>
<end>7394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FoRC4CL: A Fine-grained Field of Research Classification and Annotated Dataset of NLP Articles
%A Ahmad, Raia Abu
%A Borisova, Ekaterina
%A Rehm, Georg
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ahmad-etal-2024-forc4cl
%X The steep increase in the number of scholarly publications has given rise to various digital repositories, libraries and knowledge graphs aimed to capture, manage, and preserve scientific data. Efficiently navigating such databases requires a system able to classify scholarly documents according to the respective research (sub-)field. However, not every digital repository possesses a relevant classification schema for categorising publications. For instance, one of the largest digital archives in Computational Linguistics (CL) and Natural Language Processing (NLP), the ACL Anthology, lacks a system for classifying papers into topics and sub-topics. This paper addresses this gap by constructing a corpus of 1,500 ACL Anthology publications annotated with their main contributions using a novel hierarchical taxonomy of core CL/NLP topics and sub-topics. The corpus is used in a shared task with the goal of classifying CL/NLP papers into their respective sub-topics.
%U https://aclanthology.org/2024.lrec-main.651
%P 7389-7394
Markdown (Informal)
[FoRC4CL: A Fine-grained Field of Research Classification and Annotated Dataset of NLP Articles](https://aclanthology.org/2024.lrec-main.651) (Ahmad et al., LREC-COLING 2024)
ACL