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

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

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

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2025

Confidentiality

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

Article name in the collection

Proc. AAAI Conf. Artif. Intell.

ISBN

—

ISSN

21595399

e-ISSN

—

Number of pages

9

Pages from-to

24614-24622

Publisher name

Association for the Advancement of Artificial Intelligence

Place of publication

—

Event location

Philadelphia

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—