Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A8SAHFFQU" target="_blank" >RIV/00216208:11320/22:8SAHFFQU - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2022.findings-naacl.87" target="_blank" >https://aclanthology.org/2022.findings-naacl.87</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2022.findings-naacl.87" target="_blank" >10.18653/v1/2022.findings-naacl.87</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks

Popis výsledku v původním jazyce

Code-switching dependency parsing stands as a challenging task due to both the scarcity of necessary resources and the structural difficulties embedded in code-switched languages. In this study, we introduce novel sequence labeling models to be used as auxiliary tasks for dependency parsing of code-switched text in a semi-supervised scheme. We show that using auxiliary tasks enhances the performance of an LSTM-based dependency parsing model and leads to better results compared to an XLM-R-based model with significantly less computational and time complexity. As the first study that focuses on multiple code-switching language pairs for dependency parsing, we acquire state-of-the-art scores on all of the studied languages. Our best models outperform the previous work by 7.4 LAS points on average.

Název v anglickém jazyce

Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks

Popis výsledku anglicky

Code-switching dependency parsing stands as a challenging task due to both the scarcity of necessary resources and the structural difficulties embedded in code-switched languages. In this study, we introduce novel sequence labeling models to be used as auxiliary tasks for dependency parsing of code-switched text in a semi-supervised scheme. We show that using auxiliary tasks enhances the performance of an LSTM-based dependency parsing model and leads to better results compared to an XLM-R-based model with significantly less computational and time complexity. As the first study that focuses on multiple code-switching language pairs for dependency parsing, we acquire state-of-the-art scores on all of the studied languages. Our best models outperform the previous work by 7.4 LAS points on average.

Druh

D - Stať ve sborníku

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

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Findings of the Association for Computational Linguistics: NAACL 2022

ISBN

978-1-955917-76-6

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

1159-1171

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Seattle, United States

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—