Can dependency parses facilitate generalization in language models? A case study of cross-lingual relation extraction

Result code in IS VaVaI

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

Result on the web

<a href="https://aclanthology.org/2025.knowledgenlp-1.28/" target="_blank" >https://aclanthology.org/2025.knowledgenlp-1.28/</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Can dependency parses facilitate generalization in language models? A case study of cross-lingual relation extraction

Original language description

In this work, we propose DEPGEN, a framework for evaluating the generalization capabilities of language models on the task of relation extraction, with dependency parses as scaffolds. We use a GNN-based framework that takes dependency parses as input and learns embeddings of entities which are augmented to a baseline multilingual encoder. We also investigate the role of dependency parses when they are included as part of the prompt to LLMs in a zero-shot learning setup.

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

Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing

ISBN

979-8-89176-229-9

ISSN

—

e-ISSN

—

Number of pages

21

Pages from-to

338-358

Publisher name

—

Place of publication

—

Event location

Albuquerque, New Mexico, USA

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—