Learning Effective and Interpretable Semantic Models using Non-Negative Sparse Embedding

Brian Murphy, Partha Pratim Talukdar, Tom Mitchell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

80 Citations (Scopus)
282 Downloads (Pure)


In this paper, we introduce an application of matrix factorization to produce corpus-derived, distributional
models of semantics that demonstrate cognitive plausibility. We find that word representations
learned by Non-Negative Sparse Embedding (NNSE), a variant of matrix factorization, are sparse,
effective, and highly interpretable. To the best of our knowledge, this is the first approach which
yields semantic representation of words satisfying these three desirable properties. Though extensive
experimental evaluations on multiple real-world tasks and datasets, we demonstrate the superiority
of semantic models learned by NNSE over other state-of-the-art baselines.
Original languageEnglish
Title of host publicationInternational Conference on Computational Linguistics (COLING 2012), Mumbai, India
PublisherAssociation for Computational Linguistics
Number of pages17
Publication statusPublished - Dec 2012


  • distributional semantics,inter-,neuro-semantics,pretability,sparse coding,vector-space models,word embeddings

Fingerprint Dive into the research topics of 'Learning Effective and Interpretable Semantic Models using Non-Negative Sparse Embedding'. Together they form a unique fingerprint.

Cite this