A Simple and Effective Approach for Fine Tuning Pre-trained Word Embeddings for Improved Text Classification
This work addresses the need for more discriminative word embeddings in text classification, particularly for Arabic and English datasets, but it is incremental as it builds on existing fine-tuning methods.
The authors tackled the problem of improving text classification by fine-tuning pretrained word embeddings using class information as context, resulting in considerable performance gains on Arabic and English datasets for tasks like sentiment analysis and emotion detection.
This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning process, and contributes to the final word vector for that term. As a result, words that are used distinctively within a particular class, will bear vectors that are closer to each other in the embedding space and will be more discriminative towards that class. To validate this novel approach, it was applied to three Arabic and two English datasets that have been previously used for text classification tasks such as sentiment analysis and emotion detection. In the vast majority of cases, the results obtained using the proposed approach, improved considerably.