@inproceedings{samohi-etal-2022-using,
title = "Using Cross-Lingual Part of Speech Tagging for Partially Reconstructing the Classic Language Family Tree Model",
author = "Samohi, Anat and
Weisberg Mitelman, Daniel and
Bar, Kfir",
editor = "Tahmasebi, Nina and
Montariol, Syrielle and
Kutuzov, Andrey and
Hengchen, Simon and
Dubossarsky, Haim and
Borin, Lars",
booktitle = "Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.lchange-1.8/",
doi = "10.18653/v1/2022.lchange-1.8",
pages = "78--88",
abstract = "The tree model is well known for expressing the historic evolution of languages. This model has been considered as a method of describing genetic relationships between languages. Nevertheless, some researchers question the model`s ability to predict the proximity between two languages, since it represents genetic relatedness rather than linguistic resemblance. Defining other language proximity models has been an active research area for many years. In this paper we explore a part-of-speech model for defining proximity between languages using a multilingual language model that was fine-tuned on the task of cross-lingual part-of-speech tagging. We train the model on one language and evaluate it on another; the measured performance is then used to define the proximity between the two languages. By further developing the model, we show that it can reconstruct some parts of the tree model."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samohi-etal-2022-using">
<titleInfo>
<title>Using Cross-Lingual Part of Speech Tagging for Partially Reconstructing the Classic Language Family Tree Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anat</namePart>
<namePart type="family">Samohi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Weisberg Mitelman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Tahmasebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Kutuzov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hengchen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haim</namePart>
<namePart type="family">Dubossarsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Borin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The tree model is well known for expressing the historic evolution of languages. This model has been considered as a method of describing genetic relationships between languages. Nevertheless, some researchers question the model‘s ability to predict the proximity between two languages, since it represents genetic relatedness rather than linguistic resemblance. Defining other language proximity models has been an active research area for many years. In this paper we explore a part-of-speech model for defining proximity between languages using a multilingual language model that was fine-tuned on the task of cross-lingual part-of-speech tagging. We train the model on one language and evaluate it on another; the measured performance is then used to define the proximity between the two languages. By further developing the model, we show that it can reconstruct some parts of the tree model.</abstract>
<identifier type="citekey">samohi-etal-2022-using</identifier>
<identifier type="doi">10.18653/v1/2022.lchange-1.8</identifier>
<location>
<url>https://aclanthology.org/2022.lchange-1.8/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>78</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Cross-Lingual Part of Speech Tagging for Partially Reconstructing the Classic Language Family Tree Model
%A Samohi, Anat
%A Weisberg Mitelman, Daniel
%A Bar, Kfir
%Y Tahmasebi, Nina
%Y Montariol, Syrielle
%Y Kutuzov, Andrey
%Y Hengchen, Simon
%Y Dubossarsky, Haim
%Y Borin, Lars
%S Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F samohi-etal-2022-using
%X The tree model is well known for expressing the historic evolution of languages. This model has been considered as a method of describing genetic relationships between languages. Nevertheless, some researchers question the model‘s ability to predict the proximity between two languages, since it represents genetic relatedness rather than linguistic resemblance. Defining other language proximity models has been an active research area for many years. In this paper we explore a part-of-speech model for defining proximity between languages using a multilingual language model that was fine-tuned on the task of cross-lingual part-of-speech tagging. We train the model on one language and evaluate it on another; the measured performance is then used to define the proximity between the two languages. By further developing the model, we show that it can reconstruct some parts of the tree model.
%R 10.18653/v1/2022.lchange-1.8
%U https://aclanthology.org/2022.lchange-1.8/
%U https://doi.org/10.18653/v1/2022.lchange-1.8
%P 78-88
Markdown (Informal)
[Using Cross-Lingual Part of Speech Tagging for Partially Reconstructing the Classic Language Family Tree Model](https://aclanthology.org/2022.lchange-1.8/) (Samohi et al., LChange 2022)
ACL