@inproceedings{goel-etal-2021-goodwill,
title = "Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems",
author = "Goel, Karan and
Orr, Laurel and
Rajani, Nazneen Fatema and
Vig, Jesse and
R{\'e}, Christopher",
editor = "Kim, Young-bum and
Li, Yunyao and
Rambow, Owen",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-industry.26",
doi = "10.18653/v1/2021.naacl-industry.26",
pages = "205--213",
abstract = "Named entity linking (NEL) or mapping {``}strings{''} to {``}things{''} in a knowledge base is a fundamental preprocessing step in systems that require knowledge of entities such as information extraction and question answering. In this work, we lay out and investigate two challenges faced by individuals or organizations building NEL systems. Can they directly use an off-the-shelf system? If not, how easily can such a system be repurposed for their use case? First, we conduct a study of off-the-shelf commercial and academic NEL systems. We find that most systems struggle to link rare entities, with commercial solutions lagging their academic counterparts by 10{\%}+. Second, for a use case where the NEL model is used in a sports question-answering (QA) system, we investigate how to close the loop in our analysis by repurposing the best off-the-shelf model (Bootleg) to correct sport-related errors. We show how tailoring a simple technique for patching models using weak labeling can provide a 25{\%} absolute improvement in accuracy of sport-related errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goel-etal-2021-goodwill">
<titleInfo>
<title>Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karan</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurel</namePart>
<namePart type="family">Orr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazneen</namePart>
<namePart type="given">Fatema</namePart>
<namePart type="family">Rajani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Vig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ré</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-bum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity linking (NEL) or mapping “strings” to “things” in a knowledge base is a fundamental preprocessing step in systems that require knowledge of entities such as information extraction and question answering. In this work, we lay out and investigate two challenges faced by individuals or organizations building NEL systems. Can they directly use an off-the-shelf system? If not, how easily can such a system be repurposed for their use case? First, we conduct a study of off-the-shelf commercial and academic NEL systems. We find that most systems struggle to link rare entities, with commercial solutions lagging their academic counterparts by 10%+. Second, for a use case where the NEL model is used in a sports question-answering (QA) system, we investigate how to close the loop in our analysis by repurposing the best off-the-shelf model (Bootleg) to correct sport-related errors. We show how tailoring a simple technique for patching models using weak labeling can provide a 25% absolute improvement in accuracy of sport-related errors.</abstract>
<identifier type="citekey">goel-etal-2021-goodwill</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-industry.26</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-industry.26</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>205</start>
<end>213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems
%A Goel, Karan
%A Orr, Laurel
%A Rajani, Nazneen Fatema
%A Vig, Jesse
%A Ré, Christopher
%Y Kim, Young-bum
%Y Li, Yunyao
%Y Rambow, Owen
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F goel-etal-2021-goodwill
%X Named entity linking (NEL) or mapping “strings” to “things” in a knowledge base is a fundamental preprocessing step in systems that require knowledge of entities such as information extraction and question answering. In this work, we lay out and investigate two challenges faced by individuals or organizations building NEL systems. Can they directly use an off-the-shelf system? If not, how easily can such a system be repurposed for their use case? First, we conduct a study of off-the-shelf commercial and academic NEL systems. We find that most systems struggle to link rare entities, with commercial solutions lagging their academic counterparts by 10%+. Second, for a use case where the NEL model is used in a sports question-answering (QA) system, we investigate how to close the loop in our analysis by repurposing the best off-the-shelf model (Bootleg) to correct sport-related errors. We show how tailoring a simple technique for patching models using weak labeling can provide a 25% absolute improvement in accuracy of sport-related errors.
%R 10.18653/v1/2021.naacl-industry.26
%U https://aclanthology.org/2021.naacl-industry.26
%U https://doi.org/10.18653/v1/2021.naacl-industry.26
%P 205-213
Markdown (Informal)
[Goodwill Hunting: Analyzing and Repurposing Off-the-Shelf Named Entity Linking Systems](https://aclanthology.org/2021.naacl-industry.26) (Goel et al., NAACL 2021)
ACL