<i>N</i>-gram-based Machine Translation

Mariòo, José B.; Banchs, Rafael E.; Crego, Josep Maria; Gispert, Adrià de; Lambert, Patrik; Fonollosa, José A. R.; Costa-jussà, Marta R.

doi:10.1162/coli.2006.32.4.527

Cited by 140 publications

(82 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other effective syntactic approaches in recent years have included a bilingual language model (Mariño, Banchs, Crego, de Gispert, Lambert, Fonollosa, and Costa-jussà 2006;Niehues, Herrmann, Vogel, and Waibel 2011) enhanced with some dependency information (Garmash and Monz 2014), specifically the POS tags of parent/grandparent and closest left/right siblings, and modeling a generative dependency structure on top of a classic n-gram language model (Ding and Yamamoto 2014).…”

Section: Related Workmentioning

confidence: 99%

A Generalized Dependency Tree Language Model for SMT

Richardson

Kudo

Kazawa

et al. 2016

Journal of Natural Language Processing

View full text Add to dashboard Cite

In this paper we describe a generalized dependency tree language model for machine translation. We consider in detail the question of how to define tree-based n-grams, or 't-treelets', and thoroughly explore the strengths and weaknesses of our approach by evaluating the effect on translation quality for nine major languages. In addition, we show that it is possible to attain a significant improvement in translation quality for even non-structured machine translation by reranking filtered parses of k-best string output.

show abstract

Section: Related Workmentioning

confidence: 99%

A Generalized Dependency Tree Language Model for SMT

Richardson

Kudo

Kazawa

et al. 2016

Journal of Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…N implements the bilingual n-gram approach to SMT as described in (Mariño et al, 2006;Crego and Mariño, 2007), which can be seen as an alternative to the standard phrase-based approach (Zens et al, 2002). N main features include the use of multiple n-gram language models estimated over bilingual units, source words and/or target words or any factor decomposition, lexicalized reordering, several tuple (unigram) models, etc.. As for nearly all current statistical approaches to machine translation, these models are embedded in a linear model combination.…”

Section: Introductionmentioning

confidence: 99%

Ncode: an Open Source Bilingual N-gram SMT Toolkit

Crego¹,

Yvon²,

Acebal³

2011

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

This paper describes N, an open source statistical machine translation (SMT) toolkit for translation models estimated as n-gram language models of bilingual units (tuples). This toolkit includes tools for extracting tuples, estimating models and performing translation. It can be easily coupled to several other open source toolkits to yield a complete SMT pipeline. In this article, we review the main features of the toolkit and explain how to build a translation engine with N. We also report a short comparison with the widely known M system. Results show that N outperforms M in terms of memory requirements and translation speed. N also achieves slightly higher accuracy results.

show abstract

“…GREAT is based on a bilingual language modelling approach for SMT, which is so far implemented for n-gram models based on the framework of stochastic finitestate transducers (SFSTs). The software offers room for other language models that future developers may want to incorporate, whether they are finite-state representable models (Mariño et al, 2006;Pérez et al, …”

Section: Introductionmentioning

confidence: 99%