Statistical post-editing of a rule-based machine translation system

Lagarda, Antonio-L.; Alabau, Vicent; Casacuberta, Francisco; Silva, Roberto Carlos Lyra da; D'iaz-de-Liaño, Enrique

doi:10.3115/1620853.1620913

Cited by 29 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Work on Quality Estimation metrics may make it possible to filter out poor MT sentences, presenting to the translator only those which will not likely require re-translation (Specia 2011). The new generation MT now in deployment, whether statistical or hybrid-based on grammatical rules and bilingual data-does self-learn, as post-edited output is fed back into the system, either directly as bilingual data into statistical MT (Hardt and Elming 2010) or via statistical post-editing of rule-based MT (Dugast et al 2007;Lagarda et al 2009). In this way, the more MT is used the better it becomes.…”

Section: Are Results Valid and Reliable?mentioning

confidence: 99%

Translating by post-editing: is it the way forward?

García

2011

Machine Translation

View full text Add to dashboard Cite

Translation memory tools now offer the translator to insert post-edited machine translation segments for which no match is found in the databases. The Google Translator Toolkit does this by default, advising in its Settings window: "Most users should not modify this". Post-editing of no matches appears to work on engines trained with specific bilingual data on a source written under controlled language constraints. Would this, however, work for any type of task as Google's advice implies? We have tested this by carrying out experiments with English-Chinese trainees, using the Toolkit to translate from the source text (the control group) and by post-editing (the experimental group). Results show that post-editing gains in productivity are marginal. With regard to quality, however, post-editing produces significantly better statistical results compared to translating manually. These gains in quality are observed independently of language direction, text difficulty or translator's level of performance. In light of these findings, we discuss whether translators should consider post-editing as a viable alternative to conventional translation.

show abstract

Section: Are Results Valid and Reliable?mentioning

confidence: 99%

Translating by post-editing: is it the way forward?

García

2011

Machine Translation

View full text Add to dashboard Cite

show abstract

“…The majority of such proposals employ SMT to automatically post-edit the translations proposed by rule-based systems [48,17,50,33,4]. However, statistical APE of an SMT system has also proved its effectiveness [3,40].…”

Section: Related Workmentioning

confidence: 99%

Translating without in-domain corpus: Machine translation post-editing with online learning techniques

Lagarda

Ortiz-Martínez

Alabau

et al. 2015

Computer Speech & Language

View full text Add to dashboard Cite

Globalization has dramatically increased the need of translating information from one language to another. Frequently, such translation needs should be satisfied under very tight time constraints. Machine translation (MT) techniques can constitute a solution to this overly complex problem. However, the documents to be translated in real scenarios are often limited to a specific domain, such as a particular type of medical or legal text. This situation seriously hinders the applicability of MT, since it is usually expensive to build a reliable translation system, no matter what technology is used, due to the linguistic resources that are required to build them, such as dictionaries, translation memories or parallel texts. In order to solve this problem, we propose the application of automatic post-editing in an online learning framework. Our proposed technique allows the human expert to translate in a specific domain by using a base translation system designed to work in a general domain whose output is corrected (or adapted to the specific domain) by means of an automatic post-editing module. This automatic post-editing module learns to make its corrections from user feedback in real time by means of online learning techniques. We have validated our system using different translation technologies to implement the base translation system, as well as several texts involving different domains and languages. In most cases, our results show significant improvements in terms of BLEU (up to 16 points) with respect to the baseline systems. The proposed technique works effectively when the n-grams of the document to be translated presents a certain rate of repetition, situation which is common according to the document-internal repetition property.

show abstract

“…Recognizing that SMT is better suited to correct frequent errors to appropriate expressions, some Lagarda et al 2009) have proposed to use SMT for an automatic post-editor and built an automatic post-editing module, where MT outputs are regarded as source sentences and manually post-edited/translated results as target sentences. Béchara et al (2011) investigate the impact of SPE on a standard Phrase-Based Statistical Machine Translation (PB-SMT) system, using PB-SMT both for the first-stage MT and the second stage SPE system.…”

Section: Automatic Post-editing For Translator Cat Toolsmentioning

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

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

Statistical post-editing of a rule-based machine translation system

Cited by 29 publications

References 8 publications

Translating by post-editing: is it the way forward?

Translating by post-editing: is it the way forward?

Translating without in-domain corpus: Machine translation post-editing with online learning techniques

Getting Past the Language Gap: Innovations in Machine Translation

Contact Info

Product

Resources

About