@inproceedings{sundararajan-etal-2022-error,
title = "Error Analysis of {T}o{TT}o Table-to-Text Neural {NLG} Models",
author = "Sundararajan, Barkavi and
Sripada, Somayajulu and
Reiter, Ehud",
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 Second 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-1.43/",
doi = "10.18653/v1/2022.gem-1.43",
pages = "456--470",
abstract = "We report error analysis of outputs from four Table-to-Text generation models fine-tuned on ToTTo, an open-domain English language dataset. We carried out a manual error annotation of a subset of outputs (a total of 3,016 sentences) belonging to the topic of \textit{Politics} generated by these four models. Our error annotation focused on eight categories of errors. The error analysis shows that more than 46{\%} of sentences from each of the four models have been error-free. It uncovered some of the specific classes of errors; for example, \textit{WORD} errors (mostly verbs and prepositions) are the dominant errors in all four models and are the most complex ones among other errors. \textit{NAME} (mostly nouns) and \textit{NUMBER} errors are slightly higher in two of the \textit{GeM} benchmark models, whereas \textit{DATE-DIMENSION} and \textit{OTHER} categories of errors are more common in our Table-to-Text model. This in-depth error analysis is currently guiding us in improving our Table-to-Text model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sundararajan-etal-2022-error">
<titleInfo>
<title>Error Analysis of ToTTo Table-to-Text Neural NLG Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barkavi</namePart>
<namePart type="family">Sundararajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Somayajulu</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</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 Second 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>We report error analysis of outputs from four Table-to-Text generation models fine-tuned on ToTTo, an open-domain English language dataset. We carried out a manual error annotation of a subset of outputs (a total of 3,016 sentences) belonging to the topic of Politics generated by these four models. Our error annotation focused on eight categories of errors. The error analysis shows that more than 46% of sentences from each of the four models have been error-free. It uncovered some of the specific classes of errors; for example, WORD errors (mostly verbs and prepositions) are the dominant errors in all four models and are the most complex ones among other errors. NAME (mostly nouns) and NUMBER errors are slightly higher in two of the GeM benchmark models, whereas DATE-DIMENSION and OTHER categories of errors are more common in our Table-to-Text model. This in-depth error analysis is currently guiding us in improving our Table-to-Text model.</abstract>
<identifier type="citekey">sundararajan-etal-2022-error</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.43</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.43/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>456</start>
<end>470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Error Analysis of ToTTo Table-to-Text Neural NLG Models
%A Sundararajan, Barkavi
%A Sripada, Somayajulu
%A Reiter, Ehud
%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 Second 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 sundararajan-etal-2022-error
%X We report error analysis of outputs from four Table-to-Text generation models fine-tuned on ToTTo, an open-domain English language dataset. We carried out a manual error annotation of a subset of outputs (a total of 3,016 sentences) belonging to the topic of Politics generated by these four models. Our error annotation focused on eight categories of errors. The error analysis shows that more than 46% of sentences from each of the four models have been error-free. It uncovered some of the specific classes of errors; for example, WORD errors (mostly verbs and prepositions) are the dominant errors in all four models and are the most complex ones among other errors. NAME (mostly nouns) and NUMBER errors are slightly higher in two of the GeM benchmark models, whereas DATE-DIMENSION and OTHER categories of errors are more common in our Table-to-Text model. This in-depth error analysis is currently guiding us in improving our Table-to-Text model.
%R 10.18653/v1/2022.gem-1.43
%U https://aclanthology.org/2022.gem-1.43/
%U https://doi.org/10.18653/v1/2022.gem-1.43
%P 456-470
Markdown (Informal)
[Error Analysis of ToTTo Table-to-Text Neural NLG Models](https://aclanthology.org/2022.gem-1.43/) (Sundararajan et al., GEM 2022)
ACL
- Barkavi Sundararajan, Somayajulu Sripada, and Ehud Reiter. 2022. Error Analysis of ToTTo Table-to-Text Neural NLG Models. In Proceedings of the Second Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 456–470, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.