Rule-Based Translation with Statistical Phrase-Based Post-Editing

By Michel Simard, Nicola Ueffing, Pierre Isabelle, Roland Kuhn. 2007

187 citations recorded by the source corpus.

This article describes a machine translation system based on an automatic post-editing strategy: initially translate the input text into the target-language using a rule-based MT system, then automatically post-edit the output using a statistical phrase-based system. An implementation of this approach based on the SYSTRAN and PORTAGE MT systems was used in the shared task of the Second Workshop on Statistical Machine Translation. Experimental results on the test data of the previous campaign are presented.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey (2022, background): “Text editing is a decades-old subfield of NLP that has traditionally focused on fixing errors in machine translation (Chollampatt et al., 2020; Simard et al., 2007; Chatterjee et al., 2020) or grammar in human-written text (Wang et al., 2020b).”
(Meta-) Evaluation of Machine Translation (2007, background): “, 2007) systran-nrc National Research Council, Canada (Simard et al., 2007) ucb University of California at Berkeley, USA (Nakov and Hearst, 2007) uedin University of Edinburgh, UK (Koehn and Schroeder, 2007) umd University of Maryland, USA (Dyer, 2007) upc University of Catalonia, Spain (Costa-Juss”
Investigations on large-scale lightly-supervised training for statistical machine translation. (2008, background): “There are several directions of research to improve the genericity of SMT systems, for instance factored translation model [3], the integration of high quality dictionaries [4] or statistical post-editing of rule-based systems [ 5 , 6]. In t his work we investigate whether large-scale unsupervised t”
Pushing the Limits of Translation Quality Estimation (2017, background): “A second contribution of this paper is bringing in the related task of automatic post-editing (APE; Simard et al. (2007)), which aims to au-Source”
Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation (2017, background): “A relatively recent line of research has tried to build models which correct errors in MT automatically (Simard et al., 2007; Bojar et al., 2015; Junczys-Dowmunt and Grundkiewicz, 2016).”
“This sentence is wrong.” Detecting errors in machine-translated sentences (2011, background): “Conﬁdence estimates could beneﬁt automatic post edition systems like the one proposed in (Simard et al., 2007), by selecting which sentences are to be post edited.”
USAAR: An Operation Sequential Model for Automatic Statistical Post-Editing (2016, methodology): “Table 3 shows that, there are two types of baseline systems: (i) Baseline1 – based on raw MT output and (ii) Baseline2 – based on Statistical APE (Simard et al., 2007b) (a phrase-based system (Koehn et al., 2007)”
USAAR-SAPE: An English–Spanish Statistical Automatic Post-Editing System (2015, methodology): “Simard et al. (2007a) and Simard et al. (2007b) have shown how a PBSMT system can be used for automatic post-editing of an RBMT system for translations from English to French and French to English.”