@inproceedings{morger-2023-limits,
title = "Are There Any Limits to {E}nglish-{S}wedish Language Transfer? A Fine-grained Analysis Using Natural Language Inference",
author = "Morger, Felix",
editor = "Ilinykh, Nikolai and
Morger, Felix and
Dann{\'e}lls, Dana and
Dobnik, Simon and
Megyesi, Be{\'a}ta and
Nivre, Joakim",
booktitle = "Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)",
month = may,
year = "2023",
address = "T{\'o}rshavn, the Faroe Islands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.resourceful-1.5/",
pages = "30--41",
abstract = "The developments of deep learning in natural language processing (NLP) in recent years have resulted in an unprecedented amount of computational power and data required to train state-of-the-art NLP models. This makes lower-resource languages, such as Swedish, increasingly more reliant on language transfer effects from English since they do not have enough data to train separate monolingual models. In this study, we investigate whether there is any potential loss in English-Swedish language transfer by evaluating two types of language transfer on the GLUE/SweDiagnostics datasets and comparing between different linguistic phenomena. The results show that for an approach using machine translation for training there is no considerable loss in overall performance nor by any particular linguistic phenomena, while relying on pre-training of a multilingual model results in considerable loss in performance. This raises questions about the role of machine translation and the use of natural language inference (NLI) as well as parallel corpora for measuring English-Swedish language transfer."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morger-2023-limits">
<titleInfo>
<title>Are There Any Limits to English-Swedish Language Transfer? A Fine-grained Analysis Using Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)</title>
</titleInfo>
<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">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</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>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tórshavn, the Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The developments of deep learning in natural language processing (NLP) in recent years have resulted in an unprecedented amount of computational power and data required to train state-of-the-art NLP models. This makes lower-resource languages, such as Swedish, increasingly more reliant on language transfer effects from English since they do not have enough data to train separate monolingual models. In this study, we investigate whether there is any potential loss in English-Swedish language transfer by evaluating two types of language transfer on the GLUE/SweDiagnostics datasets and comparing between different linguistic phenomena. The results show that for an approach using machine translation for training there is no considerable loss in overall performance nor by any particular linguistic phenomena, while relying on pre-training of a multilingual model results in considerable loss in performance. This raises questions about the role of machine translation and the use of natural language inference (NLI) as well as parallel corpora for measuring English-Swedish language transfer.</abstract>
<identifier type="citekey">morger-2023-limits</identifier>
<location>
<url>https://aclanthology.org/2023.resourceful-1.5/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>30</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are There Any Limits to English-Swedish Language Transfer? A Fine-grained Analysis Using Natural Language Inference
%A Morger, Felix
%Y Ilinykh, Nikolai
%Y Morger, Felix
%Y Dannélls, Dana
%Y Dobnik, Simon
%Y Megyesi, Beáta
%Y Nivre, Joakim
%S Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Tórshavn, the Faroe Islands
%F morger-2023-limits
%X The developments of deep learning in natural language processing (NLP) in recent years have resulted in an unprecedented amount of computational power and data required to train state-of-the-art NLP models. This makes lower-resource languages, such as Swedish, increasingly more reliant on language transfer effects from English since they do not have enough data to train separate monolingual models. In this study, we investigate whether there is any potential loss in English-Swedish language transfer by evaluating two types of language transfer on the GLUE/SweDiagnostics datasets and comparing between different linguistic phenomena. The results show that for an approach using machine translation for training there is no considerable loss in overall performance nor by any particular linguistic phenomena, while relying on pre-training of a multilingual model results in considerable loss in performance. This raises questions about the role of machine translation and the use of natural language inference (NLI) as well as parallel corpora for measuring English-Swedish language transfer.
%U https://aclanthology.org/2023.resourceful-1.5/
%P 30-41
Markdown (Informal)
[Are There Any Limits to English-Swedish Language Transfer? A Fine-grained Analysis Using Natural Language Inference](https://aclanthology.org/2023.resourceful-1.5/) (Morger, RESOURCEFUL 2023)
ACL