Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3A39YU97BJ" target="_blank" >RIV/00216208:11320/26:39YU97BJ - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1609/aaai.v39i23.34641" target="_blank" >http://dx.doi.org/10.1609/aaai.v39i23.34641</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1609/aaai.v39i23.34641" target="_blank" >10.1609/aaai.v39i23.34641</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing

Popis výsledku v původním jazyce

Pre-trained language models enhanced parsers have achieved outstanding performance in rich-resource languages. Cross-lingual dependency parsing aims to learn useful knowledge from high-resource languages to alleviate data scarcity in low-resource languages. However, effectively reducing the syntactic structure distributional bias and excavating the commonalities among languages is the key challenge for cross-lingual dependency parsing. To address this issue, we propose novel dynamic syntactic feature filtering and injecting networks based on the typical shared-private model that employs one shared and two private encoders to separate source and target language features. Concretely, a Language-Specific Filtering Network (LSFN) on private encoders emphasizes helpful information and ignores the irrelevant or harmful parts of it from the source language. Meanwhile, a Language-Invariant Injecting Network (LIIN) on the shared encoder integrates the advantages of BiLSTM and improved Transformer encoders to transcend language boundaries, thus amplifying syntactic commonalities across languages. Experiments on seven benchmark datasets show that our model achieves an average absolute gain of 1.84 UAS and 3.43 LAS compared with the shared-private model. Comparative experiments validate that both LSFN and LIIN components are complementary in transferring beneficial knowledge from source to target languages. Detailed analyses highlight that our model can effectively capture linguistic commonalities and mitigate the effect of distributional bias, showcasing its robustness and efficacy. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Název v anglickém jazyce

Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing

Popis výsledku anglicky

Pre-trained language models enhanced parsers have achieved outstanding performance in rich-resource languages. Cross-lingual dependency parsing aims to learn useful knowledge from high-resource languages to alleviate data scarcity in low-resource languages. However, effectively reducing the syntactic structure distributional bias and excavating the commonalities among languages is the key challenge for cross-lingual dependency parsing. To address this issue, we propose novel dynamic syntactic feature filtering and injecting networks based on the typical shared-private model that employs one shared and two private encoders to separate source and target language features. Concretely, a Language-Specific Filtering Network (LSFN) on private encoders emphasizes helpful information and ignores the irrelevant or harmful parts of it from the source language. Meanwhile, a Language-Invariant Injecting Network (LIIN) on the shared encoder integrates the advantages of BiLSTM and improved Transformer encoders to transcend language boundaries, thus amplifying syntactic commonalities across languages. Experiments on seven benchmark datasets show that our model achieves an average absolute gain of 1.84 UAS and 3.43 LAS compared with the shared-private model. Comparative experiments validate that both LSFN and LIIN components are complementary in transferring beneficial knowledge from source to target languages. Detailed analyses highlight that our model can effectively capture linguistic commonalities and mitigate the effect of distributional bias, showcasing its robustness and efficacy. Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

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

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proc. AAAI Conf. Artif. Intell.

ISBN

—

ISSN

21595399

e-ISSN

—

Počet stran výsledku

9

Strana od-do

24614-24622

Název nakladatele

Association for the Advancement of Artificial Intelligence

Místo vydání

—

Místo konání akce

Philadelphia

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—