@inproceedings{pawar-etal-2023-evaluating,
title = "Evaluating Cross Lingual Transfer for Morphological Analysis: a Case Study of {I}ndian Languages",
author = "Pawar, Siddhesh and
Bhattacharyya, Pushpak and
Talukdar, Partha",
editor = {Nicolai, Garrett and
Chodroff, Eleanor and
Mailhot, Frederic and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigmorphon-1.3",
doi = "10.18653/v1/2023.sigmorphon-1.3",
pages = "14--26",
abstract = "Recent advances in pretrained multilingual models such as Multilingual T5 (mT5) have facilitated cross-lingual transfer by learning shared representations across languages. Leveraging pretrained multilingual models for scaling morphology analyzers to low-resource languages is a unique opportunity that has been under-explored so far. We investigate this line of research in the context of Indian languages, focusing on two important morphological sub-tasks: root word extraction and tagging morphosyntactic descriptions (MSD), viz., gender, number, and person (GNP). We experiment with six Indian languages from two language families (Dravidian and Indo-Aryan) to train a multilingual morphology analyzers for the first time for Indian languages. We demonstrate the usability of multilingual models for few-shot cross-lingual transfer through an average 7{\%} increase in GNP tagging in a cross-lingual setting as compared to a monolingual setting through controlled experiments. We provide an overview of the state of the datasets available related to our tasks and point-out a few modeling limitations due to datasets. Lastly, we analyze the cross-lingual transfer of morphological tags for verbs and nouns, which provides a proxy for the quality of representations of word markings learned by the model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pawar-etal-2023-evaluating">
<titleInfo>
<title>Evaluating Cross Lingual Transfer for Morphological Analysis: a Case Study of Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddhesh</namePart>
<namePart type="family">Pawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Talukdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Mailhot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in pretrained multilingual models such as Multilingual T5 (mT5) have facilitated cross-lingual transfer by learning shared representations across languages. Leveraging pretrained multilingual models for scaling morphology analyzers to low-resource languages is a unique opportunity that has been under-explored so far. We investigate this line of research in the context of Indian languages, focusing on two important morphological sub-tasks: root word extraction and tagging morphosyntactic descriptions (MSD), viz., gender, number, and person (GNP). We experiment with six Indian languages from two language families (Dravidian and Indo-Aryan) to train a multilingual morphology analyzers for the first time for Indian languages. We demonstrate the usability of multilingual models for few-shot cross-lingual transfer through an average 7% increase in GNP tagging in a cross-lingual setting as compared to a monolingual setting through controlled experiments. We provide an overview of the state of the datasets available related to our tasks and point-out a few modeling limitations due to datasets. Lastly, we analyze the cross-lingual transfer of morphological tags for verbs and nouns, which provides a proxy for the quality of representations of word markings learned by the model.</abstract>
<identifier type="citekey">pawar-etal-2023-evaluating</identifier>
<identifier type="doi">10.18653/v1/2023.sigmorphon-1.3</identifier>
<location>
<url>https://aclanthology.org/2023.sigmorphon-1.3</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>14</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Cross Lingual Transfer for Morphological Analysis: a Case Study of Indian Languages
%A Pawar, Siddhesh
%A Bhattacharyya, Pushpak
%A Talukdar, Partha
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%Y Mailhot, Frederic
%Y Çöltekin, Çağrı
%S Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F pawar-etal-2023-evaluating
%X Recent advances in pretrained multilingual models such as Multilingual T5 (mT5) have facilitated cross-lingual transfer by learning shared representations across languages. Leveraging pretrained multilingual models for scaling morphology analyzers to low-resource languages is a unique opportunity that has been under-explored so far. We investigate this line of research in the context of Indian languages, focusing on two important morphological sub-tasks: root word extraction and tagging morphosyntactic descriptions (MSD), viz., gender, number, and person (GNP). We experiment with six Indian languages from two language families (Dravidian and Indo-Aryan) to train a multilingual morphology analyzers for the first time for Indian languages. We demonstrate the usability of multilingual models for few-shot cross-lingual transfer through an average 7% increase in GNP tagging in a cross-lingual setting as compared to a monolingual setting through controlled experiments. We provide an overview of the state of the datasets available related to our tasks and point-out a few modeling limitations due to datasets. Lastly, we analyze the cross-lingual transfer of morphological tags for verbs and nouns, which provides a proxy for the quality of representations of word markings learned by the model.
%R 10.18653/v1/2023.sigmorphon-1.3
%U https://aclanthology.org/2023.sigmorphon-1.3
%U https://doi.org/10.18653/v1/2023.sigmorphon-1.3
%P 14-26
Markdown (Informal)
[Evaluating Cross Lingual Transfer for Morphological Analysis: a Case Study of Indian Languages](https://aclanthology.org/2023.sigmorphon-1.3) (Pawar et al., SIGMORPHON 2023)
ACL