@inproceedings{palen-michel-etal-2021-seqscore,
title = "{S}eq{S}core: Addressing Barriers to Reproducible Named Entity Recognition Evaluation",
author = "Palen-Michel, Chester and
Holley, Nolan and
Lignos, Constantine",
booktitle = "Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eval4nlp-1.5",
doi = "10.18653/v1/2021.eval4nlp-1.5",
pages = "40--50",
abstract = "To address a looming crisis of unreproducible evaluation for named entity recognition, we propose guidelines and introduce SeqScore, a software package to improve reproducibility. The guidelines we propose are extremely simple and center around transparency regarding how chunks are encoded and scored. We demonstrate that despite the apparent simplicity of NER evaluation, unreported differences in the scoring procedure can result in changes to scores that are both of noticeable magnitude and statistically significant. We describe SeqScore, which addresses many of the issues that cause replication failures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="palen-michel-etal-2021-seqscore">
<titleInfo>
<title>SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chester</namePart>
<namePart type="family">Palen-Michel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nolan</namePart>
<namePart type="family">Holley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To address a looming crisis of unreproducible evaluation for named entity recognition, we propose guidelines and introduce SeqScore, a software package to improve reproducibility. The guidelines we propose are extremely simple and center around transparency regarding how chunks are encoded and scored. We demonstrate that despite the apparent simplicity of NER evaluation, unreported differences in the scoring procedure can result in changes to scores that are both of noticeable magnitude and statistically significant. We describe SeqScore, which addresses many of the issues that cause replication failures.</abstract>
<identifier type="citekey">palen-michel-etal-2021-seqscore</identifier>
<identifier type="doi">10.18653/v1/2021.eval4nlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.eval4nlp-1.5</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>40</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation
%A Palen-Michel, Chester
%A Holley, Nolan
%A Lignos, Constantine
%S Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F palen-michel-etal-2021-seqscore
%X To address a looming crisis of unreproducible evaluation for named entity recognition, we propose guidelines and introduce SeqScore, a software package to improve reproducibility. The guidelines we propose are extremely simple and center around transparency regarding how chunks are encoded and scored. We demonstrate that despite the apparent simplicity of NER evaluation, unreported differences in the scoring procedure can result in changes to scores that are both of noticeable magnitude and statistically significant. We describe SeqScore, which addresses many of the issues that cause replication failures.
%R 10.18653/v1/2021.eval4nlp-1.5
%U https://aclanthology.org/2021.eval4nlp-1.5
%U https://doi.org/10.18653/v1/2021.eval4nlp-1.5
%P 40-50
Markdown (Informal)
[SeqScore: Addressing Barriers to Reproducible Named Entity Recognition Evaluation](https://aclanthology.org/2021.eval4nlp-1.5) (Palen-Michel et al., Eval4NLP 2021)
ACL