Improved HMM Alignment Models for Languages with Scarce Resources

Adam Lopez; Philip Resnik

Improved HMM Alignment Models for Languages with Scarce Resources

Adam Lopez, Philip Resnik

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We introduce improvements to statistical word alignment based on the Hidden Markov Model. One improvement incorporates syntactic knowledge. Results on the workshop data show that alignment performance exceeds that of a state-of-the art system based on more complex models, resulting in over a 5.5% absolute reduction in error on Romanian-English.

Original language	English
Title of host publication	Proceedings of the ACL Workshop on Building and Using Parallel Texts
Place of Publication	Ann Arbor, Michigan
Publisher	Association for Computational Linguistics
Pages	83-86
Number of pages	4
Publication status	Published - 1 Jun 2005

Access to Document

W05-0812Final published version, 100 KB

http://www.aclweb.org/anthology/W/W05/W05-0812

Cite this

@inproceedings{5dd9fdfc674a45e4af527c58021100eb,

title = "Improved HMM Alignment Models for Languages with Scarce Resources",

abstract = "We introduce improvements to statistical word alignment based on the Hidden Markov Model. One improvement incorporates syntactic knowledge. Results on the workshop data show that alignment performance exceeds that of a state-of-the art system based on more complex models, resulting in over a 5.5% absolute reduction in error on Romanian-English.",

author = "Adam Lopez and Philip Resnik",

year = "2005",

month = jun,

day = "1",

language = "English",

pages = "83--86",

booktitle = "Proceedings of the ACL Workshop on Building and Using Parallel Texts",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Improved HMM Alignment Models for Languages with Scarce Resources

AU - Lopez, Adam

AU - Resnik, Philip

PY - 2005/6/1

Y1 - 2005/6/1

N2 - We introduce improvements to statistical word alignment based on the Hidden Markov Model. One improvement incorporates syntactic knowledge. Results on the workshop data show that alignment performance exceeds that of a state-of-the art system based on more complex models, resulting in over a 5.5% absolute reduction in error on Romanian-English.

AB - We introduce improvements to statistical word alignment based on the Hidden Markov Model. One improvement incorporates syntactic knowledge. Results on the workshop data show that alignment performance exceeds that of a state-of-the art system based on more complex models, resulting in over a 5.5% absolute reduction in error on Romanian-English.

M3 - Conference contribution

SP - 83

EP - 86

BT - Proceedings of the ACL Workshop on Building and Using Parallel Texts

PB - Association for Computational Linguistics

CY - Ann Arbor, Michigan

ER -

Improved HMM Alignment Models for Languages with Scarce Resources

Abstract

Access to Document

Fingerprint

Cite this