A Neural Probabilistic Language Model

A Neural Probabilistic Language Model (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Yoshua Bengio , Réjean Ducharme , Pascal Vincent , Christian Jauvin

Venue:	JOURNAL OF MACHINE LEARNING RESEARCH
Citations:	81 - 8 self

Versions

Version History

Metadata Version 2

User correction supplied by mph

Datum	Value	Source
TITLE	A Neural Probabilistic Language Model	INFERENCE
AUTHOR NAME	Yoshua Bengio	user correction
AUTHOR NAME	Réjean Ducharme	user correction
AUTHOR NAME	Pascal Vincent	user correction
AUTHOR NAME	Christian Jauvin	user correction
ABSTRACT	A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. This is intrinsically difficult because of the curse of dimensionality: a word sequence on which the model will be tested is likely to be different from all the word sequences seen during training. Traditional but very successful approaches based on n-grams obtain generalization by concatenating very short overlapping sequences seen in the training set. We propose to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences. The model learns simultaneously (1) a distributed representation for each word along with (2) the probability function for word sequences, expressed in terms of these representations. Generalization is obtained because a sequence of words that has never been seen before gets high probability if it is made of words that are similar (in the sense of having a nearby representation) to words forming an already seen sentence. Training such large models (with millions of parameters) within a reasonable time is itself a significant challenge. We report on experiments using neural networks for the probability function, showing on two text corpora that the proposed approach significantly improves on state-of-the-art n-gram models, and that the proposed approach allows to take advantage of longer contexts.	SVM HeaderParse 0.2
YEAR	2003	INFERENCE
VENUE	JOURNAL OF MACHINE LEARNING RESEARCH	user correction
VENUE TYPE	JOURNAL	INFERENCE
PAGES	1137--1155	INFERENCE
VOLUME	3	INFERENCE
CITATIONS	31 found	ParsCit 1.0