Learning Sparse Sentence Encoding without Supervision: An Exploration of Sparsity in Variational Autoencoders
This work addresses the problem of learning sparse sentence representations without supervision for NLP researchers, but it is incremental as it builds on existing VAE and sparsity techniques from other domains.
The paper tackled the lack of exploration of sparsity in variational autoencoders for NLP, particularly for sentence encoding, by proposing a hierarchical sparse VAE model to address stability issues in state-of-the-art methods and evaluating its impact on text classification across three datasets, showing a link between sparse representations and task performance.
It has been long known that sparsity is an effective inductive bias for learning efficient representation of data in vectors with fixed dimensionality, and it has been explored in many areas of representation learning. Of particular interest to this work is the investigation of the sparsity within the VAE framework which has been explored a lot in the image domain, but has been lacking even a basic level of exploration in NLP. Additionally, NLP is also lagging behind in terms of learning sparse representations of large units of text e.g., sentences. We use the VAEs that induce sparse latent representations of large units of text to address the aforementioned shortcomings. First, we move in this direction by measuring the success of unsupervised state-of-the-art (SOTA) and other strong VAE-based sparsification baselines for text and propose a hierarchical sparse VAE model to address the stability issue of SOTA. Then, we look at the implications of sparsity on text classification across 3 datasets, and highlight a link between performance of sparse latent representations on downstream tasks and its ability to encode task-related information.