## 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.

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 language | English |
---|---|

Title of host publication | Advances in Neural Information Processing Systems 25 |

Editors | P. Bartlett, F.C.N. Pereira, C.J.C. Burges, L. Bottou, K.Q. Weinberger |

Publisher | NIPS Foundation |

Pages | 2528-2536 |

Number of pages | 9 |

Publication status | Published - 2012 |