Curriculum-Style Fine-Grained Adaption for Unsupervised Cross-Lingual Dependency Transfer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ABJPD8TWC" target="_blank" >RIV/00216208:11320/23:BJPD8TWC - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85144009133&doi=10.1109%2fTASLP.2022.3224302&partnerID=40&md5=c6aa01ea421e5a9756a064c117e34b9c" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85144009133&doi=10.1109%2fTASLP.2022.3224302&partnerID=40&md5=c6aa01ea421e5a9756a064c117e34b9c</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/taslp.2022.3224302" target="_blank" >10.1109/taslp.2022.3224302</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Curriculum-Style Fine-Grained Adaption for Unsupervised Cross-Lingual Dependency Transfer

Popis výsledku v původním jazyce

"Unsupervised cross-lingual transfer has been shown great potentials for dependency parsing of the low-resource languages when there is no annotated treebank available. Recently, the self-training method has received increasing interests because of its state-of-the-art performance in this scenario. In this work, we advance the method further by coupling it with curriculum learning, which guides the self-training in an easy-to-hard manner. Concretely, we present a novel metric to measure the instance difficulty of a dependency parser which is trained mainly on a Treebank from a resource-rich source language. By using the metric, we divide a low-resource target language into several fine-grained sub-languages by their difficulties, and then apply iterative-self-training progressively on these sub-languages. To fully explore the auto-parsed training corpus from sub-languages, we exploit an improved parameter generation network to model the sub-languages for better representation learning. Experimental results show that our final curriculum-style self-training can outperform a range of strong baselines, leading to new state-of-the-art results on unsupervised cross-lingual dependency parsing. We also conduct detailed experimental analyses to examine the proposed approach in depth for comprehensive understandings. © 2014 IEEE."

Název v anglickém jazyce

Curriculum-Style Fine-Grained Adaption for Unsupervised Cross-Lingual Dependency Transfer

Popis výsledku anglicky

"Unsupervised cross-lingual transfer has been shown great potentials for dependency parsing of the low-resource languages when there is no annotated treebank available. Recently, the self-training method has received increasing interests because of its state-of-the-art performance in this scenario. In this work, we advance the method further by coupling it with curriculum learning, which guides the self-training in an easy-to-hard manner. Concretely, we present a novel metric to measure the instance difficulty of a dependency parser which is trained mainly on a Treebank from a resource-rich source language. By using the metric, we divide a low-resource target language into several fine-grained sub-languages by their difficulties, and then apply iterative-self-training progressively on these sub-languages. To fully explore the auto-parsed training corpus from sub-languages, we exploit an improved parameter generation network to model the sub-languages for better representation learning. Experimental results show that our final curriculum-style self-training can outperform a range of strong baselines, leading to new state-of-the-art results on unsupervised cross-lingual dependency parsing. We also conduct detailed experimental analyses to examine the proposed approach in depth for comprehensive understandings. © 2014 IEEE."

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

"IEEE/ACM Transactions on Audio Speech and Language Processing"

ISSN

2329-9290

e-ISSN

—

Svazek periodika

31

Číslo periodika v rámci svazku

2023

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

11

Strana od-do

322-332

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85144009133