Multiview LSA: Representation Learning via Generalized CCA

Pushpendre Rastogi, Benjamin Van Durme, Raman AroraNAACL 2015 · OpenReview

Abstract

Multiview LSA (MVLSA) is a generalization of Latent Semantic Analysis (LSA) that supports the fusion of arbitrary views of data and relies on Generalized Canonical Correlation Analysis (GCCA). We present an algorithm for fast approximate computation of GCCA, which when coupled with methods for handling missing values, is general enough to approximate some recent algorithms for inducing vector representations of words. Experiments across a comprehensive collection of test-sets show our approach to be competitive with the state of the art.
BibTeX
@inproceedings{rastogi2015multiview,
  author = {Pushpendre Rastogi and Benjamin Van Durme and Raman Arora},
  title = {{Multiview LSA: Representation Learning via Generalized CCA}},
  booktitle = {Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2015},
  url = {https://openreview.net/forum?id=BJVBIXZOWH},
}

Loading related content...

Figure