CNN-LSTM-CRF for Aspect-Based Sentiment Analysis: A Joint Method Applied to French Reviews

Bamba Kane, Ali Jrad, Abderrahman Essebbar, Ophélie Guinaudeau, Valeria Chiesa, Ilhem Quénel, Stéphane Chau

2021

Abstract

Aspect Based Sentiment Analysis (ABSA) aims to detect the different aspects addressed in a text and the sentiment associated to each of them. There exists a lot of work on this topic for the English language, but only few models are adapted for French ABSA. In this paper, we propose a new model for ABSA, named CLC, which combines CNN (Convolutional Neural Network), Bidirectional LSTM (Long Short-Term Memory) and CRF (Conditional Random Field). We demonstrate herein its great performance on the SemEval2016 French dataset. We prove that our CLC model outperforms the state-of-the-art models for French ABSA. We also prove that CLC is well adapted for other languages such as English. One main strength of CLC is its ability to detect the aspects and the associated sentiments in a joint manner, unlike the state-of-the-art models which detect them separately.

Download


Paper Citation


in Harvard Style

Kane B., Jrad A., Essebbar A., Guinaudeau O., Chiesa V., Quénel I. and Chau S. (2021). CNN-LSTM-CRF for Aspect-Based Sentiment Analysis: A Joint Method Applied to French Reviews.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-484-8, pages 498-505. DOI: 10.5220/0010382604980505


in Bibtex Style

@conference{nlpinai21,
author={Bamba Kane and Ali Jrad and Abderrahman Essebbar and Ophélie Guinaudeau and Valeria Chiesa and Ilhem Quénel and Stéphane Chau},
title={CNN-LSTM-CRF for Aspect-Based Sentiment Analysis: A Joint Method Applied to French Reviews},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2021},
pages={498-505},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010382604980505},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - CNN-LSTM-CRF for Aspect-Based Sentiment Analysis: A Joint Method Applied to French Reviews
SN - 978-989-758-484-8
AU - Kane B.
AU - Jrad A.
AU - Essebbar A.
AU - Guinaudeau O.
AU - Chiesa V.
AU - Quénel I.
AU - Chau S.
PY - 2021
SP - 498
EP - 505
DO - 10.5220/0010382604980505