A cost-benefit analysis of cross-lingual transfer methods

An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rosa, Guilherme Moraes, Bonifacio, Luiz Henrique, de Souza, Leandro Rodrigues, Lotufo, Roberto, Nogueira, Rodrigo
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Rosa, Guilherme Moraes
Bonifacio, Luiz Henrique
de Souza, Leandro Rodrigues
Lotufo, Roberto
Nogueira, Rodrigo
description An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate that the best cross-lingual method is highly task-dependent. Finally, by combining zero-shot and translation methods, we achieve the state-of-the-art in two of the three datasets used in this work. Based on these results, we question the need for manually labeled training data in a target language. Code and translated datasets are available at https://github.com/unicamp-dl/cross-lingual-analysis
doi_str_mv 10.48550/arxiv.2105.06813
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2105_06813</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2105_06813</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-3d78c894615643c0eed6e679c2680fc25a6984b9c7624d4c4baf708d483959a13</originalsourceid><addsrcrecordid>eNotj71uwjAYAL10QJQHYMIv4GDH9md7RIhSJCQW9uiLf1pLIanstCpvX5V2uu10R8ha8EZZrfkWy3f-alrBdcPBCrkgbkf9VGfWxzGmPFMccbjXXOmUqC9TrWzI49snDnQuONYUC73F-X0K9Zk8JRxqXP1zSa4vh-v-lZ0vx9N-d2YIRjIZjPXWKRAalPQ8xgARjPMtWJ58qxGcVb3zBloVlFc9JsNtUFY67VDIJdn8aR_t3UfJNyz37vehezzIH8jKQLY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A cost-benefit analysis of cross-lingual transfer methods</title><source>arXiv.org</source><creator>Rosa, Guilherme Moraes ; Bonifacio, Luiz Henrique ; de Souza, Leandro Rodrigues ; Lotufo, Roberto ; Nogueira, Rodrigo</creator><creatorcontrib>Rosa, Guilherme Moraes ; Bonifacio, Luiz Henrique ; de Souza, Leandro Rodrigues ; Lotufo, Roberto ; Nogueira, Rodrigo</creatorcontrib><description>An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate that the best cross-lingual method is highly task-dependent. Finally, by combining zero-shot and translation methods, we achieve the state-of-the-art in two of the three datasets used in this work. Based on these results, we question the need for manually labeled training data in a target language. Code and translated datasets are available at https://github.com/unicamp-dl/cross-lingual-analysis</description><identifier>DOI: 10.48550/arxiv.2105.06813</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Information Retrieval ; Computer Science - Learning</subject><creationdate>2021-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2105.06813$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2105.06813$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Rosa, Guilherme Moraes</creatorcontrib><creatorcontrib>Bonifacio, Luiz Henrique</creatorcontrib><creatorcontrib>de Souza, Leandro Rodrigues</creatorcontrib><creatorcontrib>Lotufo, Roberto</creatorcontrib><creatorcontrib>Nogueira, Rodrigo</creatorcontrib><title>A cost-benefit analysis of cross-lingual transfer methods</title><description>An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate that the best cross-lingual method is highly task-dependent. Finally, by combining zero-shot and translation methods, we achieve the state-of-the-art in two of the three datasets used in this work. Based on these results, we question the need for manually labeled training data in a target language. Code and translated datasets are available at https://github.com/unicamp-dl/cross-lingual-analysis</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Information Retrieval</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71uwjAYAL10QJQHYMIv4GDH9md7RIhSJCQW9uiLf1pLIanstCpvX5V2uu10R8ha8EZZrfkWy3f-alrBdcPBCrkgbkf9VGfWxzGmPFMccbjXXOmUqC9TrWzI49snDnQuONYUC73F-X0K9Zk8JRxqXP1zSa4vh-v-lZ0vx9N-d2YIRjIZjPXWKRAalPQ8xgARjPMtWJ58qxGcVb3zBloVlFc9JsNtUFY67VDIJdn8aR_t3UfJNyz37vehezzIH8jKQLY</recordid><startdate>20210514</startdate><enddate>20210514</enddate><creator>Rosa, Guilherme Moraes</creator><creator>Bonifacio, Luiz Henrique</creator><creator>de Souza, Leandro Rodrigues</creator><creator>Lotufo, Roberto</creator><creator>Nogueira, Rodrigo</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210514</creationdate><title>A cost-benefit analysis of cross-lingual transfer methods</title><author>Rosa, Guilherme Moraes ; Bonifacio, Luiz Henrique ; de Souza, Leandro Rodrigues ; Lotufo, Roberto ; Nogueira, Rodrigo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-3d78c894615643c0eed6e679c2680fc25a6984b9c7624d4c4baf708d483959a13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Information Retrieval</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Rosa, Guilherme Moraes</creatorcontrib><creatorcontrib>Bonifacio, Luiz Henrique</creatorcontrib><creatorcontrib>de Souza, Leandro Rodrigues</creatorcontrib><creatorcontrib>Lotufo, Roberto</creatorcontrib><creatorcontrib>Nogueira, Rodrigo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Rosa, Guilherme Moraes</au><au>Bonifacio, Luiz Henrique</au><au>de Souza, Leandro Rodrigues</au><au>Lotufo, Roberto</au><au>Nogueira, Rodrigo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A cost-benefit analysis of cross-lingual transfer methods</atitle><date>2021-05-14</date><risdate>2021</risdate><abstract>An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate that the best cross-lingual method is highly task-dependent. Finally, by combining zero-shot and translation methods, we achieve the state-of-the-art in two of the three datasets used in this work. Based on these results, we question the need for manually labeled training data in a target language. Code and translated datasets are available at https://github.com/unicamp-dl/cross-lingual-analysis</abstract><doi>10.48550/arxiv.2105.06813</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2105.06813
ispartof
issn
language eng
recordid cdi_arxiv_primary_2105_06813
source arXiv.org
subjects Computer Science - Computation and Language
Computer Science - Information Retrieval
Computer Science - Learning
title A cost-benefit analysis of cross-lingual transfer methods
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T13%3A21%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20cost-benefit%20analysis%20of%20cross-lingual%20transfer%20methods&rft.au=Rosa,%20Guilherme%20Moraes&rft.date=2021-05-14&rft_id=info:doi/10.48550/arxiv.2105.06813&rft_dat=%3Carxiv_GOX%3E2105_06813%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true