@inproceedings{zeng-etal-2021-validating,
title = "Validating Label Consistency in {NER} Data Annotation",
author = "Zeng, Qingkai and
Yu, Mengxia and
Yu, Wenhao and
Jiang, Tianwen and
Jiang, Meng",
editor = "Gao, Yang and
Eger, Steffen and
Zhao, Wei and
Lertvittayakumjorn, Piyawat and
Fomicheva, Marina",
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-1.2/",
doi = "10.18653/v1/2021.eval4nlp-1.2",
pages = "11--15",
abstract = "Data annotation plays a crucial role in ensuring your named entity recognition (NER) projects are trained with the right information to learn from. Producing the most accurate labels is a challenge due to the complexity involved with annotation. Label inconsistency between multiple subsets of data annotation (e.g., training set and test set, or multiple training subsets) is an indicator of label mistakes. In this work, we present an empirical method to explore the relationship between label (in-)consistency and NER model performance. It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation. In experiments, our method identified the label inconsistency of test data in SCIERC and CoNLL03 datasets (with 26.7{\%} and 5.4{\%} label mistakes). It validated the consistency in the corrected version of both datasets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2021-validating">
<titleInfo>
<title>Validating Label Consistency in NER Data Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qingkai</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengxia</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianwen</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Jiang</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>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyawat</namePart>
<namePart type="family">Lertvittayakumjorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Data annotation plays a crucial role in ensuring your named entity recognition (NER) projects are trained with the right information to learn from. Producing the most accurate labels is a challenge due to the complexity involved with annotation. Label inconsistency between multiple subsets of data annotation (e.g., training set and test set, or multiple training subsets) is an indicator of label mistakes. In this work, we present an empirical method to explore the relationship between label (in-)consistency and NER model performance. It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation. In experiments, our method identified the label inconsistency of test data in SCIERC and CoNLL03 datasets (with 26.7% and 5.4% label mistakes). It validated the consistency in the corrected version of both datasets.</abstract>
<identifier type="citekey">zeng-etal-2021-validating</identifier>
<identifier type="doi">10.18653/v1/2021.eval4nlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2021.eval4nlp-1.2/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>11</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Validating Label Consistency in NER Data Annotation
%A Zeng, Qingkai
%A Yu, Mengxia
%A Yu, Wenhao
%A Jiang, Tianwen
%A Jiang, Meng
%Y Gao, Yang
%Y Eger, Steffen
%Y Zhao, Wei
%Y Lertvittayakumjorn, Piyawat
%Y Fomicheva, Marina
%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 zeng-etal-2021-validating
%X Data annotation plays a crucial role in ensuring your named entity recognition (NER) projects are trained with the right information to learn from. Producing the most accurate labels is a challenge due to the complexity involved with annotation. Label inconsistency between multiple subsets of data annotation (e.g., training set and test set, or multiple training subsets) is an indicator of label mistakes. In this work, we present an empirical method to explore the relationship between label (in-)consistency and NER model performance. It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation. In experiments, our method identified the label inconsistency of test data in SCIERC and CoNLL03 datasets (with 26.7% and 5.4% label mistakes). It validated the consistency in the corrected version of both datasets.
%R 10.18653/v1/2021.eval4nlp-1.2
%U https://aclanthology.org/2021.eval4nlp-1.2/
%U https://doi.org/10.18653/v1/2021.eval4nlp-1.2
%P 11-15
Markdown (Informal)
[Validating Label Consistency in NER Data Annotation](https://aclanthology.org/2021.eval4nlp-1.2/) (Zeng et al., Eval4NLP 2021)
ACL
- Qingkai Zeng, Mengxia Yu, Wenhao Yu, Tianwen Jiang, and Meng Jiang. 2021. Validating Label Consistency in NER Data Annotation. In Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems, pages 11–15, Punta Cana, Dominican Republic. Association for Computational Linguistics.