Improving usual Naive Bayes classifier performances with Neural Naive Bayes based models
This work addresses performance issues in sentiment analysis for practitioners using Naive Bayes, though it is incremental as it builds upon existing methods with neural enhancements.
The paper tackled the limitations of the Naive Bayes classifier, such as handling complex features and conditional independence assumptions, by introducing Neural Naive Bayes and Neural Pooled Markov Chain models, resulting in a reduction of the error rate by a factor of 4.5 on the IMDB dataset with FastText embedding.
Naive Bayes is a popular probabilistic model appreciated for its simplicity and interpretability. However, the usual form of the related classifier suffers from two major problems. First, as caring about the observations' law, it cannot consider complex features. Moreover, it considers the conditional independence of the observations given the hidden variable. This paper introduces the original Neural Naive Bayes, modeling the parameters of the classifier induced from the Naive Bayes with neural network functions. This allows to correct the first problem. We also introduce new Neural Pooled Markov Chain models, alleviating the independence condition. We empirically study the benefits of these models for Sentiment Analysis, dividing the error rate of the usual classifier by 4.5 on the IMDB dataset with the FastText embedding.