Spherical Text Embedding
This addresses a gap in NLP for tasks requiring directional similarity, offering an incremental improvement over existing methods.
The paper tackled the mismatch between Euclidean-trained text embeddings and directional similarity tasks by proposing a spherical generative model for unsupervised word and paragraph embeddings, achieving state-of-the-art performance on tasks like word similarity and document clustering with high efficiency.
Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of text embedding. To close this gap, we propose a spherical generative model based on which unsupervised word and paragraph embeddings are jointly learned. To learn text embeddings in the spherical space, we develop an efficient optimization algorithm with convergence guarantee based on Riemannian optimization. Our model enjoys high efficiency and achieves state-of-the-art performances on various text embedding tasks including word similarity and document clustering.