Enriching Parallel Corpora for Statistical Machine Translation with Semantic Negation Rephrasing

23 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.

AI and the Everything in the Whole Wide World Benchmark (2021, background): “Error analysis of a machine translation (MT) system might ﬁnd that it frequently fails on examples with negation [Wetzel and Bond, 2012, Fancellu and Webber, 2015, Hossain et al., 2020].”
How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs (2016, background): “, 2014)), and ensuring that polarity is maintained (Wetzel and Bond, 2012; Chen and Zhu, 2014; Fancellu and Webber, 2015).”
On Integrating Discourse in Machine Translation (2017, background): “…2012, 2013; Meyer and Popescu-Belis, 2012; Meyer, 2011; Meyer et al., 2011; Steele, 2015; Steele and Specia, 2016), discourse relations (Guzmán et al., 2014), pronoun prediction (Guillou, 2012; Hardmeier et al., 2013b; Guillou, 2016) and negation (Fancellu and Webber, 2014; Wetzel and Bond, 2012).”
Translating Negation: A Manual Error Analysis (2015, background): “…(2005) and Li et al. (2009) consider negation, along with other linguistic phenomena, as a problem of structural mismatch between source and target; Wetzel and Bond (2012) consider it instead as a problem of training data sparsity ; ﬁnally Baker et al. (2012) and Fancellu and Webber (2014)…”