Class Vectors: Embedding representation of Document Classes
This addresses document classification for NLP applications, but it is incremental as it builds on existing embedding methods.
The authors tackled document classification by proposing Class Vectors, which learn embeddings for classes in the same space as word and paragraph embeddings, using similarity to word vectors as features; results on sentiment analysis tasks like Yelp and Amazon reviews showed better or comparable classification performance.
Distributed representations of words and paragraphs as semantic embeddings in high dimensional data are used across a number of Natural Language Understanding tasks such as retrieval, translation, and classification. In this work, we propose "Class Vectors" - a framework for learning a vector per class in the same embedding space as the word and paragraph embeddings. Similarity between these class vectors and word vectors are used as features to classify a document to a class. In experiment on several sentiment analysis tasks such as Yelp reviews and Amazon electronic product reviews, class vectors have shown better or comparable results in classification while learning very meaningful class embeddings.