@inproceedings{mao-etal-2024-overcoming,
title = "Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing",
author = "Mao, Jiannan and
Ding, Chenchen and
Kaing, Hour and
Tanaka, Hideki and
Utiyama, Masao and
Matsumoto., Tadahiro",
editor = {Bhatia, Archna and
Bouma, Gosse and
Do{\u{g}}ru{\"o}z, A. Seza and
Evang, Kilian and
Garcia, Marcos and
Giouli, Voula and
Han, Lifeng and
Nivre, Joakim and
Rademaker, Alexandre},
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.mwe-1.10",
pages = "63--69",
abstract = "UDify is a multilingual and multi-task parser fine-tuned on mBERT that achieves remarkable performance in high-resource languages. However, the performance saturates early and decreases gradually in low-resource languages as training proceeds. This work applies a data augmentation method and conducts experiments on seven few-shot and four zero-shot languages. The unlabeled attachment scores were improved on the zero-shot languages dependency parsing tasks, with the average score rising from 67.1{\%} to 68.7{\%}. Meanwhile, dependency parsing tasks for high-resource languages and other tasks were hardly affected. Experimental results indicate the data augmentation method is effective for low-resource languages in a multilingual dependency parsing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-etal-2024-overcoming">
<titleInfo>
<title>Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiannan</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hour</namePart>
<namePart type="family">Kaing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadahiro</namePart>
<namePart type="family">Matsumoto.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Han</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>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>UDify is a multilingual and multi-task parser fine-tuned on mBERT that achieves remarkable performance in high-resource languages. However, the performance saturates early and decreases gradually in low-resource languages as training proceeds. This work applies a data augmentation method and conducts experiments on seven few-shot and four zero-shot languages. The unlabeled attachment scores were improved on the zero-shot languages dependency parsing tasks, with the average score rising from 67.1% to 68.7%. Meanwhile, dependency parsing tasks for high-resource languages and other tasks were hardly affected. Experimental results indicate the data augmentation method is effective for low-resource languages in a multilingual dependency parsing.</abstract>
<identifier type="citekey">mao-etal-2024-overcoming</identifier>
<location>
<url>https://aclanthology.org/2024.mwe-1.10</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>63</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing
%A Mao, Jiannan
%A Ding, Chenchen
%A Kaing, Hour
%A Tanaka, Hideki
%A Utiyama, Masao
%A Matsumoto., Tadahiro
%Y Bhatia, Archna
%Y Bouma, Gosse
%Y Doğruöz, A. Seza
%Y Evang, Kilian
%Y Garcia, Marcos
%Y Giouli, Voula
%Y Han, Lifeng
%Y Nivre, Joakim
%Y Rademaker, Alexandre
%S Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F mao-etal-2024-overcoming
%X UDify is a multilingual and multi-task parser fine-tuned on mBERT that achieves remarkable performance in high-resource languages. However, the performance saturates early and decreases gradually in low-resource languages as training proceeds. This work applies a data augmentation method and conducts experiments on seven few-shot and four zero-shot languages. The unlabeled attachment scores were improved on the zero-shot languages dependency parsing tasks, with the average score rising from 67.1% to 68.7%. Meanwhile, dependency parsing tasks for high-resource languages and other tasks were hardly affected. Experimental results indicate the data augmentation method is effective for low-resource languages in a multilingual dependency parsing.
%U https://aclanthology.org/2024.mwe-1.10
%P 63-69
Markdown (Informal)
[Overcoming Early Saturation on Low-Resource Languages in Multilingual Dependency Parsing](https://aclanthology.org/2024.mwe-1.10) (Mao et al., MWE-UDW-WS 2024)
ACL