Dictionary-based Domain Adaptation of MT Systems without Retraining

By Rudolf Rosa, Roman Sudarikov, Michal Novák, Martin Popel, Ondrej Bojar. 2016

4 citations recorded by the source corpus.

We describe our submission to the ITdomain translation task of WMT 2016. We perform domain adaptation with dictionary data on already trained MT systems with no further retraining. We apply our approach to two conceptually different systems developed within the QTLeap project: TectoMT and Moses, as well as Chimera, their combination. In all settings, our method improves the translation quality. Moreover, the basic variant of our approach is applicable to any MT system, including a black-box one.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Gorka Labaka
2. Eneko Agirre
3. Martin Popel
4. Mikel Artetxe
5. Luís Manuel dos Santos Gomes
6. R. Gaudio
7. Gertjan van Noord
8. K. Simov

Citations in the corpus

• Findings of the 2016 Conference on Machine Translation (2016, neutral): “Rosa et al. (2016) describe QTL-CHIMERA (Charles University).”
• SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task (2016, background): “For this specific task, where we need to work on a specific domain, an extended version of Tec-toMT was used allowing interpolation of multiple TMs (Rosa et al., 2015).”