Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs

Shay Cohen, Michael Collins

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

Abstract

We describe an approach to speed-up inference with latent-variable PCFGs, which
have been shown to be highly effective for natural language parsing. Our approach
is based on a tensor formulation recently introduced for spectral estimation of
latent-variable PCFGs coupled with a tensor decomposition algorithm well-known
in the multilinear algebra literature. We also describe an error bound for this
approximation, which gives guarantees showing that if the underlying tensors are
well approximated, then the probability distribution over trees will also be well
approximated. Empirical evaluation on real-world natural language parsing data
demonstrates a significant speed-up at minimal cost for parsing performance.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 25
EditorsP. Bartlett, F.C.N. Pereira, C.J.C. Burges, L. Bottou, K.Q. Weinberger
PublisherNIPS Foundation
Pages2528-2536
Number of pages9
Publication statusPublished - 2012

Fingerprint

Dive into the research topics of 'Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs'. Together they form a unique fingerprint.

Cite this