CUNI in WMT14: Chimera Still Awaits Bellerophon
By Ales Tamchyna, Martin Popel, Rudolf Rosa, Ondrej Bojar. 2014
11 citations recorded by the source corpus.
We present our English!Czech and English!Hindi submissions for this year’s WMT translation task. For English!Czech, we build upon last year’s CHIMERA and evaluate several setups. English!Hindi is a new language pair for this year. We experimented with reverse self-training to acquire more (synthetic) parallel data and with modeling target-side morphology.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Evaluation & Benchmarks
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
- Philipp Koehn
- Ondrej Bojar
- Lucia Specia
- Alexander M. Fraser
- Graham Neubig
- Matt Post
- Barry Haddow
- Rico Sennrich
In Computer Vision and Pattern Recognition
- Philipp Koehn
- Ondrej Bojar
- Christof Monz
- Felix Stahlberg
- Matt Post
- Alexander M. Fraser
- Lucia Specia
- Graham Neubig
In Natural Language Processing
- Philipp Koehn
- Lucia Specia
- Ondrej Bojar
- Barry Haddow
- Matt Post
- Alexander M. Fraser
- Rico Sennrich
- Christof Monz
In Evaluation & Benchmarks
- Ondrej Bojar
- Philipp Koehn
- Lucia Specia
- Barry Haddow
- Matt Post
- Christian Federmann
- Yvette Graham
- Christof Monz
Citations in the corpus
- Findings of the 2014 Workshop on Statistical Machine Translation (2014, background): “While the precise metric has varied over the years, it has always shared a common idea of computing the average number of times each system was judged better than other systems, and ranking from highest to lowest.”
- CUNI in WMT15: Chimera Strikes Again (2015, methodology): “CHIMERA (Bojar et al., 2013; Tamchyna et al., 2014) is our English-to-Czech MT system designed as a combination of three very different components:”
- CUNI-LMU Submissions in WMT2016: Chimera Constrained and Beaten (2016, methodology): “It would be best to combine these two approaches, but we did not have the time to run this setting for the WMT evaluation.”