Textual embeddings with word-type-weighted word2vec and graph neural networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F25%3A00643745" target="_blank" >RIV/67985807:_____/25:00643745 - isvavai.cz</a>

Alternative codes found

RIV/68407700:21240/25:00386773

Result on the web

<a href="https://ceur-ws.org/Vol-4092/paper8.pdf" target="_blank" >https://ceur-ws.org/Vol-4092/paper8.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Textual embeddings with word-type-weighted word2vec and graph neural networks

Original language description

The increasing use of neural networks for semantic text analysis highlights the need for more efficient methods without compromising quality. We propose a lightweight approach combining traditional word embeddings with graph convolutional networks (GCNs) to improve sentence similarity recognition. By incorporating syntactic information, such as parts of speech and grammatical functions, our method reduces computational demands at least 2.5 times while maintaining accuracy, when tested statistically indifferent to larger models.

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

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

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 25th Conference Information Technologies – Applications and Theory (ITAT 2025)

ISBN

—

ISSN

1613-0073

e-ISSN

—

Number of pages

9

Pages from-to

105-113

Publisher name

Technical University & CreateSpace Independent Publishing

Place of publication

Aachen

Event location

Telgárt

Event date

Sep 26, 2025

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

—