A Bi-recursive Auto-encoders for Learning Semantic Word Embedding

Amal Bouraoui, Salma Jamoussi, Abdelmajid Ben Hamadou

2021

Abstract

The meaning of a word depends heavily on the context in which it is embedded. Deep neural network have recorded recently a great success in representing the words’ meaning. Among them, auto-encoders based models have proven their robustness in representing the internal structure of several data. Thus, in this paper, we present a novel deep model to represent words meanings using auto-encoders and considering the left/right contexts around the word of interest. Our proposal, referred to as Bi-Recursive Auto-Encoders (Bi-RAE ), consists in modeling the meaning of a word as an evolved vector and learning its semantic features over its set of contexts.

Paper Citation

in Harvard Style

Bouraoui A., Jamoussi S. and Ben Hamadou A. (2021). A Bi-recursive Auto-encoders for Learning Semantic Word Embedding. In Proceedings of the 17th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-536-4, pages 526-533. DOI: 10.5220/0010716900003058

in Bibtex Style

@conference{webist21,
author={Amal Bouraoui and Salma Jamoussi and Abdelmajid Ben Hamadou},
title={A Bi-recursive Auto-encoders for Learning Semantic Word Embedding},
booktitle={Proceedings of the 17th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2021},
pages={526-533},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010716900003058},
isbn={978-989-758-536-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - A Bi-recursive Auto-encoders for Learning Semantic Word Embedding
SN - 978-989-758-536-4
AU - Bouraoui A.
AU - Jamoussi S.
AU - Ben Hamadou A.
PY - 2021
SP - 526
EP - 533
DO - 10.5220/0010716900003058