Word-Class Embeddings for Multiclass Text Classification
This work addresses the problem of improving multiclass text classification accuracy for NLP practitioners, but it is incremental as it builds on existing embedding methods.
The paper tackles multiclass text classification by proposing word-class embeddings (WCEs) to enhance pre-trained word embeddings with task-specific information, resulting in consistent improvements in classification accuracy across multiple neural architectures and datasets.
Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of this article) it seems appealing to enhance word representations with ad-hoc embeddings that encode task-specific information. We propose (supervised) word-class embeddings (WCEs), and show that, when concatenated to (unsupervised) pre-trained word embeddings, they substantially facilitate the training of deep-learning models in multiclass classification by topic. We show empirical evidence that WCEs yield a consistent improvement in multiclass classification accuracy, using four popular neural architectures and six widely used and publicly available datasets for multiclass text classification. Our code that implements WCEs is publicly available at https://github.com/AlexMoreo/word-class-embeddings