@inproceedings{mollanorozy-etal-2023-cross,
title = "Cross-lingual Transfer Learning with {P}ersian",
author = "Mollanorozy, Sepideh and
Tanti, Marc and
Nissim, Malvina",
editor = "Beinborn, Lisa and
Goswami, Koustava and
Murado{\u{g}}lu, Saliha and
Sorokin, Alexey and
Kumar, Ritesh and
Shcherbakov, Andreas and
Ponti, Edoardo M. and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigtyp-1.9",
doi = "10.18653/v1/2023.sigtyp-1.9",
pages = "89--95",
abstract = "The success of cross-lingual transfer learning for POS tagging has been shown to be strongly dependent, among other factors, on the (typological and/or genetic) similarity of the low-resource language used for testing and the language(s) used in pre-training or to fine-tune the model. We further unpack this finding in two directions by zooming in on a single language, namely Persian. First, still focusing on POS tagging we run an in-depth analysis of the behaviour of Persian with respect to closely related languages and languages that appear to benefit from cross-lingual transfer with Persian. To do so, we also use the World Atlas of Language Structures to determine which properties are shared between Persian and other languages included in the experiments. Based on our results, Persian seems to be a reasonable potential language for Kurmanji and Tagalog low-resource languages for other tasks as well. Second, we test whether previous findings also hold on a task other than POS tagging to pull apart the benefit of language similarity and the specific task for which such benefit has been shown to hold. We gather sentiment analysis datasets for 31 target languages and through a series of cross-lingual experiments analyse which languages most benefit from Persian as the source. The set of languages that benefit from Persian had very little overlap across the two tasks, suggesting a strong task-dependent component in the usefulness of language similarity in cross-lingual transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mollanorozy-etal-2023-cross">
<titleInfo>
<title>Cross-lingual Transfer Learning with Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sepideh</namePart>
<namePart type="family">Mollanorozy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Tanti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</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 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Beinborn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustava</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The success of cross-lingual transfer learning for POS tagging has been shown to be strongly dependent, among other factors, on the (typological and/or genetic) similarity of the low-resource language used for testing and the language(s) used in pre-training or to fine-tune the model. We further unpack this finding in two directions by zooming in on a single language, namely Persian. First, still focusing on POS tagging we run an in-depth analysis of the behaviour of Persian with respect to closely related languages and languages that appear to benefit from cross-lingual transfer with Persian. To do so, we also use the World Atlas of Language Structures to determine which properties are shared between Persian and other languages included in the experiments. Based on our results, Persian seems to be a reasonable potential language for Kurmanji and Tagalog low-resource languages for other tasks as well. Second, we test whether previous findings also hold on a task other than POS tagging to pull apart the benefit of language similarity and the specific task for which such benefit has been shown to hold. We gather sentiment analysis datasets for 31 target languages and through a series of cross-lingual experiments analyse which languages most benefit from Persian as the source. The set of languages that benefit from Persian had very little overlap across the two tasks, suggesting a strong task-dependent component in the usefulness of language similarity in cross-lingual transfer.</abstract>
<identifier type="citekey">mollanorozy-etal-2023-cross</identifier>
<identifier type="doi">10.18653/v1/2023.sigtyp-1.9</identifier>
<location>
<url>https://aclanthology.org/2023.sigtyp-1.9</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>89</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Transfer Learning with Persian
%A Mollanorozy, Sepideh
%A Tanti, Marc
%A Nissim, Malvina
%Y Beinborn, Lisa
%Y Goswami, Koustava
%Y Muradoğlu, Saliha
%Y Sorokin, Alexey
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Ponti, Edoardo M.
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F mollanorozy-etal-2023-cross
%X The success of cross-lingual transfer learning for POS tagging has been shown to be strongly dependent, among other factors, on the (typological and/or genetic) similarity of the low-resource language used for testing and the language(s) used in pre-training or to fine-tune the model. We further unpack this finding in two directions by zooming in on a single language, namely Persian. First, still focusing on POS tagging we run an in-depth analysis of the behaviour of Persian with respect to closely related languages and languages that appear to benefit from cross-lingual transfer with Persian. To do so, we also use the World Atlas of Language Structures to determine which properties are shared between Persian and other languages included in the experiments. Based on our results, Persian seems to be a reasonable potential language for Kurmanji and Tagalog low-resource languages for other tasks as well. Second, we test whether previous findings also hold on a task other than POS tagging to pull apart the benefit of language similarity and the specific task for which such benefit has been shown to hold. We gather sentiment analysis datasets for 31 target languages and through a series of cross-lingual experiments analyse which languages most benefit from Persian as the source. The set of languages that benefit from Persian had very little overlap across the two tasks, suggesting a strong task-dependent component in the usefulness of language similarity in cross-lingual transfer.
%R 10.18653/v1/2023.sigtyp-1.9
%U https://aclanthology.org/2023.sigtyp-1.9
%U https://doi.org/10.18653/v1/2023.sigtyp-1.9
%P 89-95
Markdown (Informal)
[Cross-lingual Transfer Learning with Persian](https://aclanthology.org/2023.sigtyp-1.9) (Mollanorozy et al., SIGTYP 2023)
ACL
- Sepideh Mollanorozy, Marc Tanti, and Malvina Nissim. 2023. Cross-lingual Transfer Learning with Persian. In Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 89–95, Dubrovnik, Croatia. Association for Computational Linguistics.