Statistical Phrase-Based Post-Editing

By Michel Simard, Cyril Goutte, Pierre Isabelle. 2007

217 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Findings of the 2016 Conference on Machine Translation (2016, methodology): “Nevertheless, by integrating knowledge about the source context in the learned rules, its precision is a good complement to the higher recall of (Simard et al., 2007).”
Findings of the 2015 Workshop on Statistical Machine Translation (2015, positive): “For each submitted run, the statistical signiﬁ-cance of performance differences with respect to the baseline and the re-implementation of Simard et al. (2007) is calculated with the bootstrap test (Koehn, 2004).”
Findings of the 2017 Conference on Machine Translation (WMT17) (2017, methodology): “In continuity with the previous rounds, we used as additional term of comparison a reimplementation of the method firstly proposed by Simard et al. (2007).”
SYSTRAN's Pure Neural Machine Translation Systems (2016, background): “Until recently, most of the APE approaches have been based on phrase-based SMT systems, either monolingual (MT target to human post-edition) (Simard et al., 2007) or source-1 aware (B´echara et al., 2011).”
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)”
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing (2017, methodology): “Before the application of neural sequence-to-sequence models to APE, most APE systems would rely on phrase-based SMT following a monolingual approach ﬁrst introduced by Simard et al. (2007).”
The FBK Participation in the WMT15 Automatic Post-editing Shared Task (2015, methodology): “At each stage, we study the effect of several conﬁgu-ration of each component on both the APE meth-ods ( APE-1 and APE-2 )”
Two-step translation with grammatical post-processing (2011, result): “This is somewhat the converse of other approaches (e.g. Simard et al. (2007)) where a statistical system was applied for the post-processing of a rule-based one.”
Rule-Based Translation with Statistical Phrase-Based Post-Editing (2007, methodology): “1 Introduction Simard et al. (2007) have recently shown how a statistical phrase-based machine translation system can be used as an automatic post-editing (APE) layer, on top of a rule-based machine translation system.”
A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems (2018, methodology): “In an early work, (Simard et al., 2007) combined a rule-based MT (RBMT) with a statistical MT (SMT) for monolingual post-editing.”
DFKI’s system for WMT16 IT-domain task, including analysis of systematic errors (2016, methodology): “As an alternative to automatic post-editing of the RBMT system, a serial RBMT+SMT system combination is used, as described in (Simard et al., 2007).”
Pre-Translation for Neural Machine Translation (2016, methodology): “Using the combination of SMT and RBMT, they could outperform both single systems.”
DFKI’s experimental hybrid MT system for WMT 2015 (2015, methodology): “As an alternative way of automatic post-editing of the transfer-based system, a serial transfer+ SMT system combination is used, as described in (Simard et al., 2007).”
The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task (2016, background): “The former variant (to use only MT text on the source side) was proposed by Simard et al. (2007), also known as monolingual translation, and the latter variant was proposed by B´echara et al. (2011), which is known as context-aware translation.”
Building an Arabic Machine Translation Post-Edited Corpus: Guidelines and Annotation (2016, methodology): “Successful automatic post-editing approaches using manually corrected MT output were used by Elming (2006) and Simard et al. (2007).”
Iterative Refinement for Machine Translation (2016, methodology): “Our approach differs from automatic post-editing since it does not require post-edited text which is a scarce resource (Simard et al., 2007; Bojar et al., 2016).”
Exploring the Planet of the APEs: a Comparative Study of State-of-the-art Methods for MT Automatic Post-Editing (2015, methodology): “One is the method proposed in (Simard et al., 2007), which to date is the most widely used.”