An EM algorithm for SCFG in formal syntax-based translation

Authors:
Songfang Huang; Bowen Zhou
Affiliations:
IBM T.J. Watson Research Center, Yorktown Heights, NY, USA;Centre for Speech Technology Research, University of Edinburgh, UK
Venue:
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year:
2009

Citing 0
Cited 5

Enlarged search space for SITG parsing

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Complete search space exploration for SITG inside probability

SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Two methods for extending hierarchical rules from the bilingual chart parsing

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
A $${\mathcal{O}(|G|n^6)}$$ time extension of inversion transduction grammars

Machine Translation
The IBM speech-to-speech translation system for smartphone: Improvements for resource-constrained tasks

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we investigate the use of bilingual parsing on parallel corpora to better estimate the rule parameters in a formal syntax-based machine translation system, which are normally estimated from the inaccurate heuristics. We use an Expectation-Maximization (EM) algorithm to re-estimate the parameters of synchronous context-free grammar (SCFG) rules according to the derivation knowledge from parallel corpora based on maximum likelihood principle, rather than using only the heuristic information. The proposed algorithm produces significantly better BLEU scores than a state-of-the-art formal syntax-based machine translation system on the IWSLT 2006 Chinese to English task.