Hybrid graph structure learning for improving semantic dependency parsing with robust graph neural networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3A39KZ5WTB" target="_blank" >RIV/00216208:11320/26:39KZ5WTB - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S0925231225011543#b66" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0925231225011543#b66</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.neucom.2025.130482" target="_blank" >10.1016/j.neucom.2025.130482</a>

Result language

angličtina

Original language name

Hybrid graph structure learning for improving semantic dependency parsing with robust graph neural networks

Original language description

Graph neural networks (GNN) can learn powerful representations of graphs, but their effectiveness is heavily influenced by the quality of the graph structure used. Graph structure learning (GSL) was developed to extract useful graph structures from data and learn better graph representations using GNN. GSL creates an adjacency matrix with two multilayer perceptrons and a biaffine attention network. However, it does not directly incorporate the principles of homophily, sparsity, and degree distribution, which are important in many real-life situations. Differentiable graph structure learning neural networks (DGSLN), which adhere to these basic principles, have been proven to improve GNN performance. This study proposes a GNN-based semantic dependency parsing model that incorporates the GSL adapted from the DGSLN approach to generate an initial graph. For the graph representation learning stage, we use GNN variants, GIN and GATv2, which have shown robust performance in previous research. The proposed model significantly improves previous best models, achieving an average F1 score of 93.77% on in-domain and 92.27% on out-of-domain datasets. However, our model's parsing performance is slower than prior top-performing models. The model utilizing GIN exhibits the highest level of performance and shows exceptional performance in semantic dependency parsing on English datasets. © 2025 Elsevier B.V.

Czech name

—

Czech description

—

Type

J_SC - Article in a specialist periodical, which is included in the SCOPUS database

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

Name of the periodical

Neurocomputing

ISSN

0925-2312

e-ISSN

—

Volume of the periodical

646

Issue of the periodical within the volume

2025

Country of publishing house

US - UNITED STATES

Number of pages

15

Pages from-to

130482

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-105006704207