\dm_csml_event_details UCL ELLIS

A fast and simple algorithm for training neural probabilistic language models


Speaker

Andriy Mnih

Affiliation

UCL

Date

Friday, 25 January 2013

Time

12:30-14:00

Location

Zoom

Link

Cruciform B404 - LT2

Event series

DeepMind/ELLIS CSML Seminar Series

Abstract

In spite of their superior performance, neural probabilistic language models (NPLMs) remain far less widely used than n-gram models due to their notoriously long training times, which are measured in weeks even for moderately-sized datasets. Training NPLMs is computationally expensive because they are explicitly normalized, which leads to having to consider all words in the vocabulary when computing the log-likelihood gradients.

We propose a fast and simple algorithm for training NPLMs based on noise-contrastive estimation, a newly-introduced procedure for estimating unnormalized continuous distributions. We investigate the behaviour of the algorithm on the Penn Treebank corpus and show that it reduces the training times by more than an order of magnitude without affecting the quality of the resulting models. The algorithm is also more efficient and much more stable than importance sampling because it requires far fewer noise samples to perform well.

We demonstrate the scalability of the proposed approach by training several neural language models on a 47M-word corpus with a 80K-word vocabulary, obtaining state-of-the-art results on the Microsoft Research Sentence Completion Challenge dataset.

Slides for the talk: PDF

Biography