@inproceedings{kumar-etal-2022-diversity,
title = "{''}Diversity and Uncertainty in Moderation{''} are the Key to Data Selection for Multilingual Few-shot Transfer",
author = "Kumar, Shanu and
Dandapat, Sandipan and
Choudhury, Monojit",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.78",
doi = "10.18653/v1/2022.findings-naacl.78",
pages = "1042--1055",
abstract = "Few-shot transfer often shows substantial gain over zero-shot transfer (CITATION), which is a practically useful trade-off between fully supervised and unsupervised learning approaches for multilingual pretained model-based systems. This paper explores various strategies for selecting data for annotation that can result in a better few-shot transfer. The proposed approaches rely on multiple measures such as data entropy using $n$-gram language model, predictive entropy, and gradient embedding. We propose a loss embedding method for sequence labeling tasks, which induces diversity and uncertainty sampling similar to gradient embedding. The proposed data selection strategies are evaluated and compared for POS tagging, NER, and NLI tasks for up to 20 languages. Our experiments show that the gradient and loss embedding-based strategies consistently outperform random data selection baselines, with gains varying with the initial performance of the zero-shot transfer. Furthermore, the proposed method shows similar trends in improvement even when the model is fine-tuned using a lower proportion of the original task-specific labeled training data for zero-shot transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2022-diversity">
<titleInfo>
<title>”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shanu</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Dandapat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot transfer often shows substantial gain over zero-shot transfer (CITATION), which is a practically useful trade-off between fully supervised and unsupervised learning approaches for multilingual pretained model-based systems. This paper explores various strategies for selecting data for annotation that can result in a better few-shot transfer. The proposed approaches rely on multiple measures such as data entropy using n-gram language model, predictive entropy, and gradient embedding. We propose a loss embedding method for sequence labeling tasks, which induces diversity and uncertainty sampling similar to gradient embedding. The proposed data selection strategies are evaluated and compared for POS tagging, NER, and NLI tasks for up to 20 languages. Our experiments show that the gradient and loss embedding-based strategies consistently outperform random data selection baselines, with gains varying with the initial performance of the zero-shot transfer. Furthermore, the proposed method shows similar trends in improvement even when the model is fine-tuned using a lower proportion of the original task-specific labeled training data for zero-shot transfer.</abstract>
<identifier type="citekey">kumar-etal-2022-diversity</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.78</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.78</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1042</start>
<end>1055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer
%A Kumar, Shanu
%A Dandapat, Sandipan
%A Choudhury, Monojit
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F kumar-etal-2022-diversity
%X Few-shot transfer often shows substantial gain over zero-shot transfer (CITATION), which is a practically useful trade-off between fully supervised and unsupervised learning approaches for multilingual pretained model-based systems. This paper explores various strategies for selecting data for annotation that can result in a better few-shot transfer. The proposed approaches rely on multiple measures such as data entropy using n-gram language model, predictive entropy, and gradient embedding. We propose a loss embedding method for sequence labeling tasks, which induces diversity and uncertainty sampling similar to gradient embedding. The proposed data selection strategies are evaluated and compared for POS tagging, NER, and NLI tasks for up to 20 languages. Our experiments show that the gradient and loss embedding-based strategies consistently outperform random data selection baselines, with gains varying with the initial performance of the zero-shot transfer. Furthermore, the proposed method shows similar trends in improvement even when the model is fine-tuned using a lower proportion of the original task-specific labeled training data for zero-shot transfer.
%R 10.18653/v1/2022.findings-naacl.78
%U https://aclanthology.org/2022.findings-naacl.78
%U https://doi.org/10.18653/v1/2022.findings-naacl.78
%P 1042-1055
Markdown (Informal)
[”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer](https://aclanthology.org/2022.findings-naacl.78) (Kumar et al., Findings 2022)
ACL