Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning
This work addresses efficiency and quality issues in document embeddings for NLP, IR, and recommendation systems, but it is incremental as it builds on existing contrastive learning methods.
The paper tackles the challenge of efficiently learning quality embeddings for long documents by combining a self-contrastive siamese network with a neural Bregman network, showing improved performance in topic classification tasks on legal and biomedical datasets.
Learning quality document embeddings is a fundamental problem in natural language processing (NLP), information retrieval (IR), recommendation systems, and search engines. Despite recent advances in the development of transformer-based models that produce sentence embeddings with self-contrastive learning, the encoding of long documents (Ks of words) is still challenging with respect to both efficiency and quality considerations. Therefore, we train Longfomer-based document encoders using a state-of-the-art unsupervised contrastive learning method (SimCSE). Further on, we complement the baseline method -- siamese neural network -- with additional convex neural networks based on functional Bregman divergence aiming to enhance the quality of the output document representations. We show that overall the combination of a self-contrastive siamese network and our proposed neural Bregman network outperforms the baselines in two linear classification settings on three long document topic classification tasks from the legal and biomedical domains.