@inproceedings{chandu-etal-2022-denoising,
title = "Denoising Large-Scale Image Captioning from Alt-text Data Using Content Selection Models",
author = "Chandu, Khyathi Raghavi and
Sharma, Piyush and
Changpinyo, Soravit and
Thapliyal, Ashish V. and
Soricut, Radu",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.532",
pages = "6089--6104",
abstract = "Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples that are expensive to curate both in terms of time and man-power. Instead, alt-text based captions gathered from the web is a far cheaper alternative to scale with the downside of being noisy. Recent modeling approaches to IC often fall short in terms of performance in leveraging these noisy datasets in favor of clean annotations. We address this problem with a simple yet effective technique of breaking down the task into two smaller, more controllable tasks {--} skeleton prediction and skeleton-based caption generation. Specifically, we show that sub-selecting content words as skeletons helps in generating improved and denoised captions when leveraging rich yet noisy alt-text{--}based uncurated datasets. We also show that the predicted English skeletons can further cross-lingually be leveraged to generate non-English captions, and present experimental results covering caption generation in French, Italian, German, Spanish and Hindi. We also show that skeleton-based prediction allows for better control of certain caption properties, such as length, content, and gender expression, providing a handle to perform human-in-the-loop interpretable semi-automatic corrections.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chandu-etal-2022-denoising">
<titleInfo>
<title>Denoising Large-Scale Image Captioning from Alt-text Data Using Content Selection Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soravit</namePart>
<namePart type="family">Changpinyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Thapliyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Soricut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples that are expensive to curate both in terms of time and man-power. Instead, alt-text based captions gathered from the web is a far cheaper alternative to scale with the downside of being noisy. Recent modeling approaches to IC often fall short in terms of performance in leveraging these noisy datasets in favor of clean annotations. We address this problem with a simple yet effective technique of breaking down the task into two smaller, more controllable tasks – skeleton prediction and skeleton-based caption generation. Specifically, we show that sub-selecting content words as skeletons helps in generating improved and denoised captions when leveraging rich yet noisy alt-text–based uncurated datasets. We also show that the predicted English skeletons can further cross-lingually be leveraged to generate non-English captions, and present experimental results covering caption generation in French, Italian, German, Spanish and Hindi. We also show that skeleton-based prediction allows for better control of certain caption properties, such as length, content, and gender expression, providing a handle to perform human-in-the-loop interpretable semi-automatic corrections.</abstract>
<identifier type="citekey">chandu-etal-2022-denoising</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.532</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6089</start>
<end>6104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Denoising Large-Scale Image Captioning from Alt-text Data Using Content Selection Models
%A Chandu, Khyathi Raghavi
%A Sharma, Piyush
%A Changpinyo, Soravit
%A Thapliyal, Ashish V.
%A Soricut, Radu
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F chandu-etal-2022-denoising
%X Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples that are expensive to curate both in terms of time and man-power. Instead, alt-text based captions gathered from the web is a far cheaper alternative to scale with the downside of being noisy. Recent modeling approaches to IC often fall short in terms of performance in leveraging these noisy datasets in favor of clean annotations. We address this problem with a simple yet effective technique of breaking down the task into two smaller, more controllable tasks – skeleton prediction and skeleton-based caption generation. Specifically, we show that sub-selecting content words as skeletons helps in generating improved and denoised captions when leveraging rich yet noisy alt-text–based uncurated datasets. We also show that the predicted English skeletons can further cross-lingually be leveraged to generate non-English captions, and present experimental results covering caption generation in French, Italian, German, Spanish and Hindi. We also show that skeleton-based prediction allows for better control of certain caption properties, such as length, content, and gender expression, providing a handle to perform human-in-the-loop interpretable semi-automatic corrections.
%U https://aclanthology.org/2022.coling-1.532
%P 6089-6104
Markdown (Informal)
[Denoising Large-Scale Image Captioning from Alt-text Data Using Content Selection Models](https://aclanthology.org/2022.coling-1.532) (Chandu et al., COLING 2022)
ACL