@inproceedings{huidrom-belz-2022-survey,
title = "A Survey of Recent Error Annotation Schemes for Automatically Generated Text",
author = "Huidrom, Rudali and
Belz, Anya",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.33",
doi = "10.18653/v1/2022.gem-1.33",
pages = "383--398",
abstract = "While automatically computing numerical scores remains the dominant paradigm in NLP system evaluation, error analysis is receiving increasing attention, with numerous error annotation schemes being proposed for automatically generated text. However, there is little agreement about what error annotation schemes should look like, how many different types of errors should be distinguished and at what level of granularity. In this paper, our aim is to map out recent work on annotating errors in automatically generated text, with a particular focus on error taxonomies. We describe our systematic paper selection process, and survey the error annotation schemes reported in the papers, drawing out similarities and differences between them. Finally, we characterise the issues that would make it difficult to move from the current situation to a standardised error taxonomy for annotating errors in automatically generated text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huidrom-belz-2022-survey">
<titleInfo>
<title>A Survey of Recent Error Annotation Schemes for Automatically Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rudali</namePart>
<namePart type="family">Huidrom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While automatically computing numerical scores remains the dominant paradigm in NLP system evaluation, error analysis is receiving increasing attention, with numerous error annotation schemes being proposed for automatically generated text. However, there is little agreement about what error annotation schemes should look like, how many different types of errors should be distinguished and at what level of granularity. In this paper, our aim is to map out recent work on annotating errors in automatically generated text, with a particular focus on error taxonomies. We describe our systematic paper selection process, and survey the error annotation schemes reported in the papers, drawing out similarities and differences between them. Finally, we characterise the issues that would make it difficult to move from the current situation to a standardised error taxonomy for annotating errors in automatically generated text.</abstract>
<identifier type="citekey">huidrom-belz-2022-survey</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.33</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.33</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>383</start>
<end>398</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Recent Error Annotation Schemes for Automatically Generated Text
%A Huidrom, Rudali
%A Belz, Anya
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F huidrom-belz-2022-survey
%X While automatically computing numerical scores remains the dominant paradigm in NLP system evaluation, error analysis is receiving increasing attention, with numerous error annotation schemes being proposed for automatically generated text. However, there is little agreement about what error annotation schemes should look like, how many different types of errors should be distinguished and at what level of granularity. In this paper, our aim is to map out recent work on annotating errors in automatically generated text, with a particular focus on error taxonomies. We describe our systematic paper selection process, and survey the error annotation schemes reported in the papers, drawing out similarities and differences between them. Finally, we characterise the issues that would make it difficult to move from the current situation to a standardised error taxonomy for annotating errors in automatically generated text.
%R 10.18653/v1/2022.gem-1.33
%U https://aclanthology.org/2022.gem-1.33
%U https://doi.org/10.18653/v1/2022.gem-1.33
%P 383-398
Markdown (Informal)
[A Survey of Recent Error Annotation Schemes for Automatically Generated Text](https://aclanthology.org/2022.gem-1.33) (Huidrom & Belz, GEM 2022)
ACL