B7: Modelling Human Translation with a Noisy Channel
Human translation is modelled on the basis of a noisy channel, as commonly done in machine translation. The two main objectives of translation, source language fidelity and target language conformity, are modelled probabilistically.
Different modes (interpreting, translation) and levels of expertise (learner, professional) are considered. The data set we use are translations of speeches from the EU Parliament which are compiled into a corpus. Computational translation models are built, which provide the basis for several studies on translationese, translation adequacy as well as translation complexity.
The 17th International Workshop on Spoken Language Translation, Seattle, WA, United States, 2020.
Analyzing variation in translation through neural semantic spaces Inproceedings
Detecting linguistic variation in translated vs. interpreted texts using relative entropy Inproceedings
Empirical Investigations in the Forms of Mediated Discourse at the European Parliament, Thematic Session at the 49th Poznan Linguistic Meeting (PLM2019), Poznan, 2019.
Meta, 63 (3), pp. 695-716, 2018.
ParlaCLARIN workshop, 11th Language Resources and Evaluation Conference (LREC2018), Miyazaki, Japan, 2018.
Exploring Variation in Translation with Relative Entropy Inproceedings
International Symposium on Parallel Corpora ECETT / PaCor 2018, Madrid, Spain, 2018.
Preserving Metadata from Parliamentary Debates Inproceedings
Fišer, Darja; Eskevich, Maria; de Jong, Franciska (Ed.): Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), European Language Resources Association (ELRA), Paris, France, 2018.