Work

Evaluating Text Representations Techniques for Hypernymy Detection: The Case of Arabic Language

Year: 2025

Type: conference-paper

Abstract: Text representation is a key performance component for any hypernymy-related task.In this study, we investigate representation techniques to understand which features best represent the hypernymy relation, focusing on three factors of representation: word embedding, embedding combination techniques, and using features.The results indicate that different embeddings have different effects on performance; concatenation, 'addition and subtraction' have led to better performance, and using unsupervised measures has a negative effect on performance.

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-89

Authors: Randah Alharbi, Husni Al-Muhtaseb

Institution: King Fahd University of Petroleum and Minerals

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: King Fahd University of Petroleum and Minerals

OpenAlex ID: W4409480956

FWCI:

Cites:

Cited by:

Related to: 10