@inproceedings{tarunesh-etal-2021-meta,
title = "Meta-Learning for Effective Multi-task and Multilingual Modelling",
author = "Tarunesh, Ishan and
Khyalia, Sushil and
Kumar, Vishwajeet and
Ramakrishnan, Ganesh and
Jyothi, Preethi",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.314",
doi = "10.18653/v1/2021.eacl-main.314",
pages = "3600--3612",
abstract = "Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g., named entity recognition in English) and knowledge of other languages (e.g., question-answering in Spanish). Such shared representations are typically learned in isolation, either across tasks or across languages. In this work, we propose a meta-learning approach to learn the interactions between both tasks and languages. We also investigate the role of different sampling strategies used during meta-learning. We present experiments on five different tasks and six different languages from the XTREME multilingual benchmark dataset. Our meta-learned model clearly improves in performance compared to competitive baseline models that also include multi-task baselines. We also present zero-shot evaluations on unseen target languages to demonstrate the utility of our proposed model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tarunesh-etal-2021-meta">
<titleInfo>
<title>Meta-Learning for Effective Multi-task and Multilingual Modelling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ishan</namePart>
<namePart type="family">Tarunesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sushil</namePart>
<namePart type="family">Khyalia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishwajeet</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g., named entity recognition in English) and knowledge of other languages (e.g., question-answering in Spanish). Such shared representations are typically learned in isolation, either across tasks or across languages. In this work, we propose a meta-learning approach to learn the interactions between both tasks and languages. We also investigate the role of different sampling strategies used during meta-learning. We present experiments on five different tasks and six different languages from the XTREME multilingual benchmark dataset. Our meta-learned model clearly improves in performance compared to competitive baseline models that also include multi-task baselines. We also present zero-shot evaluations on unseen target languages to demonstrate the utility of our proposed model.</abstract>
<identifier type="citekey">tarunesh-etal-2021-meta</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.314</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.314</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>3600</start>
<end>3612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta-Learning for Effective Multi-task and Multilingual Modelling
%A Tarunesh, Ishan
%A Khyalia, Sushil
%A Kumar, Vishwajeet
%A Ramakrishnan, Ganesh
%A Jyothi, Preethi
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F tarunesh-etal-2021-meta
%X Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g., named entity recognition in English) and knowledge of other languages (e.g., question-answering in Spanish). Such shared representations are typically learned in isolation, either across tasks or across languages. In this work, we propose a meta-learning approach to learn the interactions between both tasks and languages. We also investigate the role of different sampling strategies used during meta-learning. We present experiments on five different tasks and six different languages from the XTREME multilingual benchmark dataset. Our meta-learned model clearly improves in performance compared to competitive baseline models that also include multi-task baselines. We also present zero-shot evaluations on unseen target languages to demonstrate the utility of our proposed model.
%R 10.18653/v1/2021.eacl-main.314
%U https://aclanthology.org/2021.eacl-main.314
%U https://doi.org/10.18653/v1/2021.eacl-main.314
%P 3600-3612
Markdown (Informal)
[Meta-Learning for Effective Multi-task and Multilingual Modelling](https://aclanthology.org/2021.eacl-main.314) (Tarunesh et al., EACL 2021)
ACL
- Ishan Tarunesh, Sushil Khyalia, Vishwajeet Kumar, Ganesh Ramakrishnan, and Preethi Jyothi. 2021. Meta-Learning for Effective Multi-task and Multilingual Modelling. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3600–3612, Online. Association for Computational Linguistics.