@inproceedings{agarwal-nenkova-2023-named,
title = "Named Entity Recognition in a Very Homogenous Domain",
author = "Agarwal, Oshin and
Nenkova, Ani",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.138",
doi = "10.18653/v1/2023.findings-eacl.138",
pages = "1850--1855",
abstract = "Machine Learning models have lower accuracy when tested on out-of-domain data. Developing models that perform well on several domains or can be quickly adapted to a new domain is an important research area. Domain, however, is a vague term, that can refer to any aspect of data such as language, genre, source and structure. We consider a very homogeneous source of data, specifically sentences from news articles from the same newspaper in English, and collect a dataset of such {``}in-domain{''} sentences annotated with named entities. We find that even in such a homogeneous domain, the performance of named entity recognition models varies significantly across news topics. Selection of diverse data, as we demonstrate, is crucial even in a seemingly homogeneous domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-nenkova-2023-named">
<titleInfo>
<title>Named Entity Recognition in a Very Homogenous Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oshin</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ani</namePart>
<namePart type="family">Nenkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine Learning models have lower accuracy when tested on out-of-domain data. Developing models that perform well on several domains or can be quickly adapted to a new domain is an important research area. Domain, however, is a vague term, that can refer to any aspect of data such as language, genre, source and structure. We consider a very homogeneous source of data, specifically sentences from news articles from the same newspaper in English, and collect a dataset of such “in-domain” sentences annotated with named entities. We find that even in such a homogeneous domain, the performance of named entity recognition models varies significantly across news topics. Selection of diverse data, as we demonstrate, is crucial even in a seemingly homogeneous domain.</abstract>
<identifier type="citekey">agarwal-nenkova-2023-named</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.138</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.138</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1850</start>
<end>1855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition in a Very Homogenous Domain
%A Agarwal, Oshin
%A Nenkova, Ani
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F agarwal-nenkova-2023-named
%X Machine Learning models have lower accuracy when tested on out-of-domain data. Developing models that perform well on several domains or can be quickly adapted to a new domain is an important research area. Domain, however, is a vague term, that can refer to any aspect of data such as language, genre, source and structure. We consider a very homogeneous source of data, specifically sentences from news articles from the same newspaper in English, and collect a dataset of such “in-domain” sentences annotated with named entities. We find that even in such a homogeneous domain, the performance of named entity recognition models varies significantly across news topics. Selection of diverse data, as we demonstrate, is crucial even in a seemingly homogeneous domain.
%R 10.18653/v1/2023.findings-eacl.138
%U https://aclanthology.org/2023.findings-eacl.138
%U https://doi.org/10.18653/v1/2023.findings-eacl.138
%P 1850-1855
Markdown (Informal)
[Named Entity Recognition in a Very Homogenous Domain](https://aclanthology.org/2023.findings-eacl.138) (Agarwal & Nenkova, Findings 2023)
ACL