Evaluating the Combination of Word Embeddings with Mixture of Experts and Cascading gcForest In Identifying Sentiment Polarity

Abstract

Neural word embeddings have been able to deliver impressive results in many Natural Language Processing tasks. The quality of the word embedding determines the performance of a supervised model. However, choosing the right set of word embeddings for a given dataset is a major challenging task for enhancing the results. In this paper, we have evaluated neural word embeddings with (i) a mixture of classification experts (MoCE) model for sentiment classification task, (ii) to compare and improve the classification accuracy by different combination of word embedding as first level of features and pass it to cascade model inspired by GcForest for extracting diverse features. We argue that each expert learns a certain positive and negative examples corresponding to its category of features and resulting features on a given task (polarity identification) can achieve competitive performance with state of the art methods in terms of accuracy, precision, and recall using gcForest.