@inproceedings{maronikolakis-etal-2023-improving,
title = "Improving Few-Shot Learning with Multilingual Transfer and {M}onte {C}arlo Training Set Selection",
author = {Maronikolakis, Antonis and
O{'}Grady, Paul and
Sch{\"u}tze, Hinrich and
Lyra, Matti},
editor = "Breitholtz, Ellen and
Lappin, Shalom and
Loaiciga, Sharid and
Ilinykh, Nikolai and
Dobnik, Simon",
booktitle = "Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)",
month = sep,
year = "2023",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clasp-1.1",
pages = "1--10",
abstract = "In industry settings, machine learning is an attractive tool to automatize processes. Unfortunately, annotated and high-quality data is expensive to source. This problem is exacerbated in settings spanning multiple markets and languages. Thus, developing solutions for multilingual tasks with little available data is challenging. Few-shot learning is a compelling approach when building solutions in multilingual and low-resource settings, since the method not only requires just a few training examples to achieve high performance, but is also a technique agnostic to language. Even though the technique can be applied to multilingual settings, optimizing performance is an open question. In our work we show that leveraging higher-resource, task-specific language data can boost overall performance and we propose a method to select training examples per their average performance in a Monte Carlo simulation, resulting in a training set more conducive to learning. We demonstrate the effectiveness of our methods in fashion text reviews moderation, classifying reviews as related or unrelated to the given product. We show that our methodology boosts performance in multilingual (English, French, German) settings, increasing F1 score and significantly decreasing false positives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maronikolakis-etal-2023-improving">
<titleInfo>
<title>Improving Few-Shot Learning with Multilingual Transfer and Monte Carlo Training Set Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Maronikolakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">O’Grady</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matti</namePart>
<namePart type="family">Lyra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shalom</namePart>
<namePart type="family">Lappin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In industry settings, machine learning is an attractive tool to automatize processes. Unfortunately, annotated and high-quality data is expensive to source. This problem is exacerbated in settings spanning multiple markets and languages. Thus, developing solutions for multilingual tasks with little available data is challenging. Few-shot learning is a compelling approach when building solutions in multilingual and low-resource settings, since the method not only requires just a few training examples to achieve high performance, but is also a technique agnostic to language. Even though the technique can be applied to multilingual settings, optimizing performance is an open question. In our work we show that leveraging higher-resource, task-specific language data can boost overall performance and we propose a method to select training examples per their average performance in a Monte Carlo simulation, resulting in a training set more conducive to learning. We demonstrate the effectiveness of our methods in fashion text reviews moderation, classifying reviews as related or unrelated to the given product. We show that our methodology boosts performance in multilingual (English, French, German) settings, increasing F1 score and significantly decreasing false positives.</abstract>
<identifier type="citekey">maronikolakis-etal-2023-improving</identifier>
<location>
<url>https://aclanthology.org/2023.clasp-1.1</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Few-Shot Learning with Multilingual Transfer and Monte Carlo Training Set Selection
%A Maronikolakis, Antonis
%A O’Grady, Paul
%A Schütze, Hinrich
%A Lyra, Matti
%Y Breitholtz, Ellen
%Y Lappin, Shalom
%Y Loaiciga, Sharid
%Y Ilinykh, Nikolai
%Y Dobnik, Simon
%S Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)
%D 2023
%8 September
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F maronikolakis-etal-2023-improving
%X In industry settings, machine learning is an attractive tool to automatize processes. Unfortunately, annotated and high-quality data is expensive to source. This problem is exacerbated in settings spanning multiple markets and languages. Thus, developing solutions for multilingual tasks with little available data is challenging. Few-shot learning is a compelling approach when building solutions in multilingual and low-resource settings, since the method not only requires just a few training examples to achieve high performance, but is also a technique agnostic to language. Even though the technique can be applied to multilingual settings, optimizing performance is an open question. In our work we show that leveraging higher-resource, task-specific language data can boost overall performance and we propose a method to select training examples per their average performance in a Monte Carlo simulation, resulting in a training set more conducive to learning. We demonstrate the effectiveness of our methods in fashion text reviews moderation, classifying reviews as related or unrelated to the given product. We show that our methodology boosts performance in multilingual (English, French, German) settings, increasing F1 score and significantly decreasing false positives.
%U https://aclanthology.org/2023.clasp-1.1
%P 1-10
Markdown (Informal)
[Improving Few-Shot Learning with Multilingual Transfer and Monte Carlo Training Set Selection](https://aclanthology.org/2023.clasp-1.1) (Maronikolakis et al., CLASP 2023)
ACL