@inproceedings{chang-etal-2022-shot,
title = "Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning",
author = "Chang, Ernie and
Alabi, Jesujoba O. and
Adelani, David Ifeoluwa and
Demberg, Vera",
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-1.377",
pages = "4286--4291",
abstract = "The surging demand for multilingual dialogue systems often requires a costly labeling process for each language addition. For low resource languages, human annotators are continuously tasked with the adaptation of resource-rich language utterances for each new domain. However, this prohibitive and impractical process can often be a bottleneck for low resource languages that are still without proper translation systems nor parallel corpus. In particular, it is difficult to obtain task-specific low resource language annotations for the English-derived creoles (e.g. Nigerian and Cameroonian Pidgin). To address this issue, we utilize the pretrained language models i.e. BART which has shown great potential in language generation/understanding {--} we propose to finetune the BART model to generate utterances in Pidgin by leveraging the proximity of the source and target languages, and utilizing positive and negative examples in constrastive training objectives. We collected and released the first parallel Pidgin-English conversation corpus in two dialogue domains and showed that this simple and effective technique is suffice to yield impressive results for English-to-Pidgin generation, which are two closely-related languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2022-shot">
<titleInfo>
<title>Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernie</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</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>The surging demand for multilingual dialogue systems often requires a costly labeling process for each language addition. For low resource languages, human annotators are continuously tasked with the adaptation of resource-rich language utterances for each new domain. However, this prohibitive and impractical process can often be a bottleneck for low resource languages that are still without proper translation systems nor parallel corpus. In particular, it is difficult to obtain task-specific low resource language annotations for the English-derived creoles (e.g. Nigerian and Cameroonian Pidgin). To address this issue, we utilize the pretrained language models i.e. BART which has shown great potential in language generation/understanding – we propose to finetune the BART model to generate utterances in Pidgin by leveraging the proximity of the source and target languages, and utilizing positive and negative examples in constrastive training objectives. We collected and released the first parallel Pidgin-English conversation corpus in two dialogue domains and showed that this simple and effective technique is suffice to yield impressive results for English-to-Pidgin generation, which are two closely-related languages.</abstract>
<identifier type="citekey">chang-etal-2022-shot</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.377</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4286</start>
<end>4291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning
%A Chang, Ernie
%A Alabi, Jesujoba O.
%A Adelani, David Ifeoluwa
%A Demberg, Vera
%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 chang-etal-2022-shot
%X The surging demand for multilingual dialogue systems often requires a costly labeling process for each language addition. For low resource languages, human annotators are continuously tasked with the adaptation of resource-rich language utterances for each new domain. However, this prohibitive and impractical process can often be a bottleneck for low resource languages that are still without proper translation systems nor parallel corpus. In particular, it is difficult to obtain task-specific low resource language annotations for the English-derived creoles (e.g. Nigerian and Cameroonian Pidgin). To address this issue, we utilize the pretrained language models i.e. BART which has shown great potential in language generation/understanding – we propose to finetune the BART model to generate utterances in Pidgin by leveraging the proximity of the source and target languages, and utilizing positive and negative examples in constrastive training objectives. We collected and released the first parallel Pidgin-English conversation corpus in two dialogue domains and showed that this simple and effective technique is suffice to yield impressive results for English-to-Pidgin generation, which are two closely-related languages.
%U https://aclanthology.org/2022.coling-1.377
%P 4286-4291
Markdown (Informal)
[Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning](https://aclanthology.org/2022.coling-1.377) (Chang et al., COLING 2022)
ACL
- Ernie Chang, Jesujoba O. Alabi, David Ifeoluwa Adelani, and Vera Demberg. 2022. Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4286–4291, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.