Statistical Post-Editing for a Statistical MT System

By Hannah Béchara, Yanjun Ma, Josef van Genabith. 2011

64 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 2015 Workshop on Statistical Machine Translation (2015, methodology): “The problem is exacerbated by the “context-aware” approach proposed by B´echara et al. (2011), which builds the phrase table by joining source and target tokens thus breaking down the co-occurrence counts into smaller numbers.”
Exploring the Planet of the APEs: a Comparative Study of State-of-the-art Methods for MT Automatic Post-Editing (2015, background): “…in the work by Simard et al. (2007) and inspired a number of further investigations (Isabelle et al., 2007; Dugast et al., 2007; Dugast et al., 2009; Lagarda et al., 2009; B´echara et al., 2011; B´echara et al., 2012; Rubino et al., 2012; Rosa et al., 2013; Lagarda et al., 2014, inter alia).”
Can Automatic Post-Editing Improve NMT? (2020, methodology): “Earlier application of statistical phrase-based models for APE treated it as a monolingual re-writing task without considering the source sentence (Simard et al., 2007; Béchara et al., 2011).”
Multilingual Neural Machine Translation for Zero-Resource Languages (2019, methodology): “For instance, in statistical machine translation (SMT), Oﬂazer and El-Kahlout (2007) and Béchara, Ma, and van Genabith (2011) showed how the output of a translation model can be used iteratively to improve results in a task like post-editing.”
A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems (2018, methodology): “In 2011, (B´echara et al., 2011) proposed the ﬁrst model based on contextual post-editing, showing improvements over monolingual approaches.”
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing (2017, methodology): “Béchara et al. (2011) proposed a “source-context aware” variant of this approach where automatically created word alignments were used to create a new source language which consisted of joined MT output and source token pairs.”
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.”