Identification of translationese: a machine learning approach

This paper presents a machine learning approach to the study of translationese. The goal is to train a computer system to distinguish between translated and non-translated text, in order to determine the characteristic features that influence the classifiers. Several algorithms reach up to 97.62% success rate on a technical dataset. Moreover, the SVM classifier consistently reports a statistically significant improved accuracy when the learning system benefits from the addition of simplification features to the basic translational classifier system. Therefore, these findings may be considered an argument for the existence of the Simplification Universal.

Citation

Ilisei I., Inkpen D., Corpas Pastor G., Mitkov R. (2010) Identification of Translationese: A Machine Learning Approach. In: Gelbukh A. (Ed.) Computational Linguistics and Intelligent Text Processing: 11th International Conference, CICLing 2010, Iasi, Romania, March 21-27, 2010, Proceedings. Berlin, Heidelberg: Springer Verlag, pp. 503-511.

Type

Conference contribution

Language

en

Series/Report no.

Lecture Notes in Computer Science, vol. 6008

ISSN

0302-9743

Collections

Research Institute in Information and Language Processing