Multiview LSA: Representation Learning via Generalized CCA

descriptionPublicationkeyboard_double_arrow_right Article , Conference object 01 Jan 2015Publisher:Association for Computational Linguistics (ACL)Journal:Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Authors: Pushpendre Rastogi; Benjamin Van Durme; Raman Arora;

doi: 10.3115/v1/n15-1058 , 10.5281/zenodo.16710

Multiview LSA: Representation Learning via Generalized CCA

- Summary
- Subjects
- Metrics

Abstract

This is the companion data for the paper, `"Multiview LSA: Representation Learning Via Generalized CCA", Pushpendre Rastogi, Benjamin Van Durme and Raman Arora, NAACL(2015).` For more details see http://cs.jhu.edu/~prastog3/mvlsa @conference{rastogi2015multiview, Author = {Pushpendre Rastogi, Benjamin {Van Durme} and Raman Arora}, Booktitle = {Proceedings of NAACL}, Keywords = {mvlsa,multiview lsa,mvppdb}, Title = {Multiview LSA: Representation Learning Via Generalized CCA}, Year = {2015} } This data contains vocabulary files used, embeddings created and intermediate co-occurrence counts that were extracted from various sources.

Related Organizations

Johns Hopkins University
United States

Keywords

mvlsa, data

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	29
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Top 10%
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 10%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 10%