A discriminative model for tree-to-tree translation

Cowan, Brooke; Kučerová, Ivona; Collins, Michael

doi:10.3115/1610075.1610110

Cited by 32 publications

(26 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Approaches include word substitution systems (Brown et al 1993), phrase substitution systems Och and Ney 2004), and synchronous context-free grammar systems (Wu and Wong 1998;Chiang 2005;Wong et al 2005;), all of which train on string pairs and seek to establish connections between source and target strings. By contrast, explicit syntax approaches seek to model directly the relations learned from parsed data, including models between source trees and target trees (Gildea 2003;Eisner 2003;Melamed 2004;Cowan et al 2006), source trees and target strings (Quirk et al 2001;Galley et al 2004). A strength of phrase models is that they can acquire all phrase pairs consistent with computed word alignments , concatenate those phrases together, and re-order them under several cost models.…”

Section: Syntax Based Approaches: From Hierarchical To Sbsmtmentioning

confidence: 99%

See 1 more Smart Citation

Getting Past the Language Gap: Innovations in Machine Translation

Delmonte

2012

Mobile Speech and Advanced Natural Language Solutions

View full text Add to dashboard Cite

In this chapter, we will be reviewing state of the art machine translation systems, and will discuss innovative methods for machine translation, highlighting the most promising techniques and applications. Machine translation (MT) has benefited from a revitalization in the last 10 years or so, after a period of relatively slow activity. In 2005 the field received a jumpstart when a powerful complete experimental package for building MT systems from scratch became freely available as a result of the unified efforts of the MOSES international consortium. Around the same time, hierarchical methods had been introduced by Chinese researchers, which allowed the introduction and use of syntactic information in translation modeling. Furthermore, the advances in the related field of computational linguistics, making off-the-shelf taggers and parsers readily available, helped give MT an additional boost. Yet there is still more progress to be made. For example, MT will be enhanced greatly when both syntax and semantics are on board: this still presents a major challenge though many advanced research groups are currently pursuing ways to meet this challenge head-on. The next generation of MT will consist of a collection of hybrid systems. It also augurs well for the mobile environment, as we look forward to more advanced and improved technologies that enable the working of Speech-To-Speech machine translation on hand-held devices, i.e. speech recognition and speech synthesis. We review all of these developments and point out in the final section some of the most promising research avenues for the future of MT.

show abstract

Section: Syntax Based Approaches: From Hierarchical To Sbsmtmentioning

confidence: 99%

“…Some studies incorporate structural information into the alignment process after this simple word alignment (Quirk et al 2005;Cowan et al 2006). However, this is not sufficient because the basic word alignment itself is not good.…”

Section: Hierarchical Mtmentioning

confidence: 99%

Getting Past the Language Gap: Innovations in Machine Translation

Delmonte

2012

Mobile Speech and Advanced Natural Language Solutions

View full text Add to dashboard Cite

show abstract

“…There is a growing body of work on the use of syntax for improving statistical machine translation, from approaches such as (Chiang, 2007) that use "formal syntax", that is syntactic structures for the source and target that are discovered on the basis of a bilingual corpus, but without resort to an externally motivated parser, to approaches such as (Yamada and Knight, 2001) and (Marcu et al, 2006) that use an external parser on the target only, or such as (Quirk et al, 2005) on the source only, or such as (Cowan et al, 2006) that use external parsers both on the source and on the target.…”

Section: Related Workmentioning

confidence: 99%

Experiments in discriminating phrase-based translations on the basis of syntactic coupling features

Nikoulina

Dymetman

2008

Proceedings of the Second Workshop on Syntax and Structure in Statistical Translation - SSST '08

View full text Add to dashboard Cite

We describe experiments on discriminating English to French phrase-based translations through the use of syntactic "coupling" features. Using a robust rule-based dependency parser, we parse both the English source and the French translation candidates from the nbest list returned by our phrase-based system; we compute for each candidate a number of coupling features, that is, values that depend on the amount of alignment between edges in the source and target structures, and discriminatively train the weights of these coupling features. We compare different feature combinations. Although the improvements in terms of automatic measures such as Bleu and Nist are inconclusive, an initial human assessment of the results appears to show certain qualitative improvements.

show abstract

“…First, there is a growing body of empirical evidence from a number of fields [11,1,4,20] along with theoretical results [12] suggesting that discriminative training outperforms generative training when enough data is available. Second, unlike generative training methods, our discriminative approach does not make strong independence assumptions about the features, which would ignore important dependencies.…”

Section: Introductionmentioning

confidence: 99%