To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Neural Models for Detecti… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Neural Models for Detecting Binary Semantic Textual Similarity for Algerian and MSA

Conference paper
Authors Wafia Adouane
Jean-Philippe Bernardy
Simon Dobnik
Published in Proceedings of the Fourth Arabic Natural Language Processing Workshop WANLP 2019 at ACL, Florence, Italy, August 1, 2019.
ISBN 978-1-950737-32-1
Publisher Association for Computational Linguistics
Place of publication Florence, Italy
Publication year 2019
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Subject categories Language Technology (Computational Linguistics), Computational linguistics


We explore the extent to which neural networks can learn to identify semantically equivalent sentences from a small variable dataset using an end-to-end training. We collect a new noisy non-standardised user-generated Algerian (ALG) dataset and also translate it to Modern Standard Arabic (MSA) which serves as its regularised counterpart. We compare the performance of various models on both datasets and report the best performing configurations. The results show that relatively simple models composed of 2 LSTM layers outperform by far other more sophisticated attention-based architectures, for both ALG and MSA datasets.

Page Manager: Webmaster|Last update: 9/11/2012

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?