Translation Task : Two-step Data Selection and RBMT-Style Synthetic Rules

By Raphaël Rubino, Antonio Toral, Víctor M. Sánchez-Cartagena, Jorge Ferrández-Tordera, Sergio Ortiz Rojas, Gema Ramírez-Sánchez, Felipe Sánchez-Martínez, Andy Way. 2014

Subfields: 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 Natural Language Processing

1. Philipp Koehn
2. Lucia Specia
3. Ondrej Bojar
4. Barry Haddow
5. Matt Post
6. Christof Monz
7. Rico Sennrich
8. Graham Neubig

Citations in the corpus

• Findings of the 2014 Workshop on Statistical Machine Translation (2014, methodology): “A rank range was collected for each system across these folds; the average value was used to order the systems, and a 95% confidence interval across these ranks was used to organize the systems into equivalence classes containing systems with over-18 lapping ranges.”
• Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling (2015, methodology): “The out-of-domain part of osubs is further processed with vocabulary saturation (Lewis and Eetemadi, 2013) in order to have a more efficient and compact system (Rubino et al., 2014).”