Improving aspect-based neural sentiment classification with lexicon enhancement, attention regularization and sentiment induction

Deep neural networks as an end-to-end approach lack robustness from an application point of view, as it is very difficult to fix an obvious problem without retraining the model, for example, when a model consistently predicts positive when seeing the word “terrible.” Meanwhile, it is less stressed t...

Full description

Bibliographic Details
Authors: Bao, Lingxian, Lambert, Patrik, Badia Cardus, Toni
Format: article
Status:Published version
Publication Date:2023
Country:España
Institution:Universitat Pompeu Fabra
Repository:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/56255
Online Access:http://hdl.handle.net/10230/56255
http://dx.doi.org/10.1017/S1351324922000432
Access Level:Open access
Keyword:Sentiment Analysis
Deep Learning
Attention
Lexicon
Domain Adaptation
Description
Summary:Deep neural networks as an end-to-end approach lack robustness from an application point of view, as it is very difficult to fix an obvious problem without retraining the model, for example, when a model consistently predicts positive when seeing the word “terrible.” Meanwhile, it is less stressed that the commonly used attention mechanism is likely to “over-fit” by being overly sparse, so that some key positions in the input sequence could be overlooked by the network. To address these problems, we proposed a lexicon-enhanced attention LSTM model in 2019, named ATLX. In this paper, we describe extended experiments and analysis of the ATLX model. And, we also try to further improve the aspect-based sentiment analysis system by combining a vector-based sentiment domain adaptation method.