Skip to yearly menu bar Skip to main content


Workshop

SpectralWords: Spectral Embeddings Approach to Word Similarity Task for Large Vocabularies

Ivan Lobov

East Meeting Level 8 + 15 #11

Wed 2 May, 11 a.m. PDT

In this paper we show how recent advances in spectral clustering using Bethe Hessian operator can be used to learn dense word representations. We propose an algorithm SpectralWords that achieves comparable to the state-of-the-art performance on word similarity tasks for medium-size vocabularies and can be superior for datasets with larger vocabularies.

Live content is unavailable. Log in and register to view live content