Structured Language Models for . . .

Structured Language Models for . . . (2009)

Cached

Download Links

by Ying Zhang

Versions

Version History

Metadata Version 1

User correction supplied by mph

Datum	Value	Source
TITLE	Structured Language Models for . . .	user correction
AUTHOR NAME	Ying Zhang	user correction
AUTHOR AFFIL	Language Technologies Institute; School of Computer Science; Carnegie Mellon University	user correction
AUTHOR ADDR	5000 Forbes Ave., Pittsburgh, PA 15213	user correction
ABSTRACT	Language model plays an important role in statistical machine translation systems. It is the key knowledge source to determine the right word order of the translation. Standard n-gram based language model predicts the next word based on the n − 1 immediate left context. Increasing the order of n and the size of the training data improves the performance of the LM as shown by the suffix array language model and distributed language model systems. However, such improvements narrow down very fast after n reaches 6. To improve the n-gram language model, we also developed dynamic n-gram language model adaptation and discriminative language model to tackle issues with the standard n-gram language models and observed improvements in the translation qualities. The fact is that human beings do not reuse long n-grams to create new sentences. Rather, we reuse the structure (grammar) and replace constituents to construct new sentences. Structured language model tries to model the structural information in natural language, especially the long-distance dependencies in a probabilistic framework. However, exploring and using structural information is computationally expensive, as the number of possible structures for a sentence is very large even with the constraint of a grammar. It is difficult to apply parsers on data that is different from the training data of the treebank and parsers are usually hard to scale up. In this	user correction
YEAR	2009	SVM HeaderParse 0.2
CITATIONS	114 found	ParsCit 1.0