Modelling the Semantic Change Dynamics using Diachronic Word Embedding

Mohamed Boukhaled, Benjamin Fagard, Thierry Poibeau

2019

Abstract

In this contribution, we propose a computational model to predict the semantic evolution of words over time. Though semantic change is very complex and not well suited to analytical manipulation, we believe that computational modelling is a crucial tool to study such phenomenon. Our aim is to capture the systemic change of word’s meanings in an empirical model that can also predict this type of change, making it falsifiable. The model that we propose is based on the long short-term memory units architecture of recurrent neural networks trained on diachronic word embeddings. In order to illustrate the significance of this kind of empirical model, we then conducted an experimental evaluation using the Google Books NGram corpus. The results show that the model is effective in capturing the semantic change and can achieve a high degree of accuracy on predicting words’ distributional semantics.

Download


Paper Citation


in Harvard Style

Boukhaled M., Fagard B. and Poibeau T. (2019). Modelling the Semantic Change Dynamics using Diachronic Word Embedding.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: NLPinAI, ISBN 978-989-758-350-6, pages 944-951. DOI: 10.5220/0007698109440951


in Bibtex Style

@conference{nlpinai19,
author={Mohamed Boukhaled and Benjamin Fagard and Thierry Poibeau},
title={Modelling the Semantic Change Dynamics using Diachronic Word Embedding},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: NLPinAI,},
year={2019},
pages={944-951},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007698109440951},
isbn={978-989-758-350-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: NLPinAI,
TI - Modelling the Semantic Change Dynamics using Diachronic Word Embedding
SN - 978-989-758-350-6
AU - Boukhaled M.
AU - Fagard B.
AU - Poibeau T.
PY - 2019
SP - 944
EP - 951
DO - 10.5220/0007698109440951