Work

Methodical Evaluation of Arabic Word Embeddings

Year: 2017

Type: conference-paper

Abstract: Many unsupervised learning techniques have been proposed to obtain meaningful representations of words from text.In this study, we evaluate these various techniques when used to generate Arabic word embeddings.We first build a benchmark for the Arabic language that can be utilized to perform intrinsic evaluation of different word embeddings.We then perform additional extrinsic evaluations of the embeddings based on two NLP tasks.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/p17-2072

Authors: Mohammed Elrazzaz, Shady Elbassuoni, Khaled Shaban, Chadi Helwe

Institutions: Qatar University, American University of Beirut

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Qatar Foundation, Fonds National de la Recherche Luxembourg, Qatar National Research Fund

Award: G1525618996