Language Models for Machine Translation: Original vs. Translated Texts

By Gennadi Lembersky, Noam Ordan, Shuly Wintner. 2011

112 citations recorded by the source corpus.

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

TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages (2020, background): “The result is that a corpus of so-called Translationese may be markedly different from purely native text (Lembersky et al., 2012; Volansky et al., 2013; Avner et al., 2014; Eetemadi and Toutanova, 2014; Rabinovich and Wintner, 2015; Wintner, 2016).”
APE at Scale and Its Implications on MT Evaluation Biases (2019, background): “Lembersky et al. (2012); Stymne (2017) explored how the translation direction for statistical machine translation affects the translation result.”
Asymmetric Features Of Human Generated Translation (2014, methodology): “…validation of linguistic theories about Translationese (Volansky et al., 2013), and second, improving statistical machine translation by leveraging the knowledge of the translation direction in training and test data (Lember- 159 sky et al., 2012a; Lembersky et al., 2013; Lembersky et al., 2012b).”
On the features of translationese (2015, unknown): “The contribution of knowledge of the translation direction to machine translation is further corroborated in a series of works (Lembersky et al., 2011, 2012a,b). van Halteren (2008) shows that there are significant differences between texts translated from different source languages to the same…”
Large-Scale Machine Translation between Arabic and Hebrew: Available Corpora and Initial Results (2016, background): “Work on Hebrew translation is more limited, but previous studies on translating Hebrew to English also demonstrated the need for morphological analysis and tokenization (Lavie et al., 2004; Lembersky et al., 2012; Singh and Habash, 2012).”
Sheffield Systems for the Finnish-English WMT Translation Task (2015, methodology): “of the training data makes a significant difference for both the translation model and the language model (Kurokawa et al., 2009; Lembersky et al., 2013; Lembersky et al., 2012).”