Dependency Scoring Learning and Corpus Boosting for Translation-Based Cross-Lingual Dependency Parsing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3A9J9UNDVG" target="_blank" >RIV/00216208:11320/26:9J9UNDVG - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1145/3748315" target="_blank" >http://dx.doi.org/10.1145/3748315</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3748315" target="_blank" >10.1145/3748315</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Dependency Scoring Learning and Corpus Boosting for Translation-Based Cross-Lingual Dependency Parsing

Popis výsledku v původním jazyce

Dependency parsing is a fundamental task in natural language processing that involves identifying the grammatical relationships between words in a sentence. One promising approach for performing this task in languages lacking annotated treebanks is treebank translation, which utilizes word alignments to map dependencies from a source treebank to the corresponding target translation. However, due to language differences and the limitations of word alignment tools, this method would inevitably generate noise during mapping. To reduce the effect of noise, we first exploit MetaNet to compute quality scores for each dependency and identify low-score ones as noise. MetaNet is a fake teacher that learns to score homework (dependencies) by comparing answers from the top student (strong parser) and the regular student (weak parser) without knowing the correct answer (gold-standard). With the scoring capability of MetaNet, we design an iterative algorithm to boost the target treebank quality, which trains with high-quality dependencies and relabels the low-quality dependencies. Our method achieves better results than the originally translated treebanks and shows highly competitive performances with prior methods on the Universal Dependency Treebanks v2.2. We also provide detailed analysis and discussions. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Název v anglickém jazyce

Dependency Scoring Learning and Corpus Boosting for Translation-Based Cross-Lingual Dependency Parsing

Popis výsledku anglicky

Dependency parsing is a fundamental task in natural language processing that involves identifying the grammatical relationships between words in a sentence. One promising approach for performing this task in languages lacking annotated treebanks is treebank translation, which utilizes word alignments to map dependencies from a source treebank to the corresponding target translation. However, due to language differences and the limitations of word alignment tools, this method would inevitably generate noise during mapping. To reduce the effect of noise, we first exploit MetaNet to compute quality scores for each dependency and identify low-score ones as noise. MetaNet is a fake teacher that learns to score homework (dependencies) by comparing answers from the top student (strong parser) and the regular student (weak parser) without knowing the correct answer (gold-standard). With the scoring capability of MetaNet, we design an iterative algorithm to boost the target treebank quality, which trains with high-quality dependencies and relabels the low-quality dependencies. Our method achieves better results than the originally translated treebanks and shows highly competitive performances with prior methods on the Universal Dependency Treebanks v2.2. We also provide detailed analysis and discussions. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

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

2025

Kód důvěrnosti údajů

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

Název periodika

ACM Transactions on Asian and Low-Resource Language Information Processing

ISSN

2375-4699

e-ISSN

—

Svazek periodika

24

Číslo periodika v rámci svazku

8

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

9

Strana od-do

83

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105018459708