@inproceedings{khan-etal-2022-ban,
title = "{BAN}-Cap: A Multi-Purpose {E}nglish-{B}angla Image Descriptions Dataset",
author = "Khan, Mohammad Faiyaz and
Shifath, S.M. Sadiq-Ur-Rahman and
Islam, Md Saiful",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.740",
pages = "6855--6865",
abstract = "As computers have become efficient at understanding visual information and transforming it into a written representation, research interest in tasks like automatic image captioning has seen a significant leap over the last few years. While most of the research attention is given to the English language in a monolingual setting, resource-constrained languages like Bangla remain out of focus, predominantly due to a lack of standard datasets. Addressing this issue, we present a new dataset BAN-Cap following the widely used Flickr8k dataset, where we collect Bangla captions of the images provided by qualified annotators. Our dataset represents a wider variety of image caption styles annotated by trained people from different backgrounds. We present a quantitative and qualitative analysis of the dataset and the baseline evaluation of the recent models in Bangla image captioning. We investigate the effect of text augmentation and demonstrate that an adaptive attention-based model combined with text augmentation using Contextualized Word Replacement (CWR) outperforms all state-of-the-art models for Bangla image captioning. We also present this dataset{'}s multipurpose nature, especially on machine translation for Bangla-English and English-Bangla. This dataset and all the models will be useful for further research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khan-etal-2022-ban">
<titleInfo>
<title>BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Faiyaz</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S.M.</namePart>
<namePart type="given">Sadiq-Ur-Rahman</namePart>
<namePart type="family">Shifath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Saiful</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As computers have become efficient at understanding visual information and transforming it into a written representation, research interest in tasks like automatic image captioning has seen a significant leap over the last few years. While most of the research attention is given to the English language in a monolingual setting, resource-constrained languages like Bangla remain out of focus, predominantly due to a lack of standard datasets. Addressing this issue, we present a new dataset BAN-Cap following the widely used Flickr8k dataset, where we collect Bangla captions of the images provided by qualified annotators. Our dataset represents a wider variety of image caption styles annotated by trained people from different backgrounds. We present a quantitative and qualitative analysis of the dataset and the baseline evaluation of the recent models in Bangla image captioning. We investigate the effect of text augmentation and demonstrate that an adaptive attention-based model combined with text augmentation using Contextualized Word Replacement (CWR) outperforms all state-of-the-art models for Bangla image captioning. We also present this dataset’s multipurpose nature, especially on machine translation for Bangla-English and English-Bangla. This dataset and all the models will be useful for further research.</abstract>
<identifier type="citekey">khan-etal-2022-ban</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.740</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6855</start>
<end>6865</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset
%A Khan, Mohammad Faiyaz
%A Shifath, S.M. Sadiq-Ur-Rahman
%A Islam, Md Saiful
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F khan-etal-2022-ban
%X As computers have become efficient at understanding visual information and transforming it into a written representation, research interest in tasks like automatic image captioning has seen a significant leap over the last few years. While most of the research attention is given to the English language in a monolingual setting, resource-constrained languages like Bangla remain out of focus, predominantly due to a lack of standard datasets. Addressing this issue, we present a new dataset BAN-Cap following the widely used Flickr8k dataset, where we collect Bangla captions of the images provided by qualified annotators. Our dataset represents a wider variety of image caption styles annotated by trained people from different backgrounds. We present a quantitative and qualitative analysis of the dataset and the baseline evaluation of the recent models in Bangla image captioning. We investigate the effect of text augmentation and demonstrate that an adaptive attention-based model combined with text augmentation using Contextualized Word Replacement (CWR) outperforms all state-of-the-art models for Bangla image captioning. We also present this dataset’s multipurpose nature, especially on machine translation for Bangla-English and English-Bangla. This dataset and all the models will be useful for further research.
%U https://aclanthology.org/2022.lrec-1.740
%P 6855-6865
Markdown (Informal)
[BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset](https://aclanthology.org/2022.lrec-1.740) (Khan et al., LREC 2022)
ACL