Kriya – An end-to-end Hierarchical Phrase-based MT System

Kriya – An end-to-end Hierarchical Phrase-based MT System (2012)

Cached

Download Links

by Baskaran Sankaran , Majid Razmara , Anoop Sarkar

Versions

Version 0

Version History

Metadata Version 0

Datum	Value	Source
TITLE	Kriya – An end-to-end Hierarchical Phrase-based MT System	SVM HeaderParse 0.2
AUTHOR NAME	Baskaran Sankaran	SVM HeaderParse 0.2
AUTHOR NAME	Majid Razmara	SVM HeaderParse 0.2
AUTHOR NAME	Anoop Sarkar	SVM HeaderParse 0.2
ABSTRACT	This paper describes Kriya — a new statistical machine translation (SMT) system that uses hierarchical phrases, which were first introduced in the Hiero machine translation system (Chiang, 2007). Kriya supports both a grammar extraction module for synchronous context-free grammars (SCFGs) and a CKY-based decoder. There are several re-implementations of Hiero in the machine translation community, but Kriya offers the following novel contributions: (a) Grammar extraction in Kriya supports extraction of the full set of Hiero-style SCFG rules but also supports the extraction of several types of compact rule sets which leads to faster decoding for different language pairs without compromising the BLEU scores. Kriya currently supports extraction of compact SCFGs such as grammars with one non-terminal and grammar pruning based on certain rule patterns, and (b) The Kriya decoder offers some unique improvements in the implementation of cube pruning, such as increasing diversity in the target language n-best output and novel methods for language model (LM) integration. The Kriya decoder can take advantage of parallelization using a networked cluster. Kriya supports KENLM and SRILM for language model queries and exploits n-gram history states in KENLM. This paper also provides several experimental results which demonstrate that the translation quality of Kriya compares favourably to the Moses (Koehn et al., 2007) phrase-based system in several language pairs while showing a substantial improvement for Chinese-English similar to Chiang (2007). We also quantify the model sizes for phrase-based and Hiero-style systems apart from presenting experiments comparing variants of Hiero models. 1.	SVM HeaderParse 0.2
YEAR	2012	SVM HeaderParse 0.2
CITATIONS	29 found	ParsCit 1.0