@inproceedings{sikasote-etal-2023-big,
title = "{BIG}-{C}: a Multimodal Multi-Purpose Dataset for {B}emba",
author = "Sikasote, Claytone and
Mukonde, Eunice and
Alam, Md Mahfuz Ibn and
Anastasopoulos, Antonios",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.115",
doi = "10.18653/v1/2023.acl-long.115",
pages = "2062--2078",
abstract = "We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on speech recognition (ASR), machine translation (MT) and speech translation (ST) tasks, and sketch out other potential future multimodal uses of our dataset. We hope that by making the dataset available to the research community, this work will foster research and encourage collaboration across the language, speech, and vision communities especially for languages outside the {``}traditionally{''} used high-resourced ones. All data and code are publicly available: [\url{https://github.com/csikasote/bigc}](\url{https://github.com/csikasote/bigc}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sikasote-etal-2023-big">
<titleInfo>
<title>BIG-C: a Multimodal Multi-Purpose Dataset for Bemba</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claytone</namePart>
<namePart type="family">Sikasote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunice</namePart>
<namePart type="family">Mukonde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Mahfuz</namePart>
<namePart type="given">Ibn</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on speech recognition (ASR), machine translation (MT) and speech translation (ST) tasks, and sketch out other potential future multimodal uses of our dataset. We hope that by making the dataset available to the research community, this work will foster research and encourage collaboration across the language, speech, and vision communities especially for languages outside the “traditionally” used high-resourced ones. All data and code are publicly available: [https://github.com/csikasote/bigc](https://github.com/csikasote/bigc).</abstract>
<identifier type="citekey">sikasote-etal-2023-big</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.115</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.115</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2062</start>
<end>2078</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BIG-C: a Multimodal Multi-Purpose Dataset for Bemba
%A Sikasote, Claytone
%A Mukonde, Eunice
%A Alam, Md Mahfuz Ibn
%A Anastasopoulos, Antonios
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sikasote-etal-2023-big
%X We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on speech recognition (ASR), machine translation (MT) and speech translation (ST) tasks, and sketch out other potential future multimodal uses of our dataset. We hope that by making the dataset available to the research community, this work will foster research and encourage collaboration across the language, speech, and vision communities especially for languages outside the “traditionally” used high-resourced ones. All data and code are publicly available: [https://github.com/csikasote/bigc](https://github.com/csikasote/bigc).
%R 10.18653/v1/2023.acl-long.115
%U https://aclanthology.org/2023.acl-long.115
%U https://doi.org/10.18653/v1/2023.acl-long.115
%P 2062-2078
Markdown (Informal)
[BIG-C: a Multimodal Multi-Purpose Dataset for Bemba](https://aclanthology.org/2023.acl-long.115) (Sikasote et al., ACL 2023)
ACL
- Claytone Sikasote, Eunice Mukonde, Md Mahfuz Ibn Alam, and Antonios Anastasopoulos. 2023. BIG-C: a Multimodal Multi-Purpose Dataset for Bemba. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2062–2078, Toronto, Canada. Association for Computational Linguistics.