@article{AvnerOrdanWintner2016,
  author    = {Avner, Ehud Alexander and Ordan, Noam and Wintner, Shuly},
  title     = {Identifying translationese at the word and sub-word level},
  series = {Digital Scholarship in the Humanities},
  volume    = {31},
  journal   = {Digital Scholarship in the Humanities},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {2055-7671},
  doi       = {10.1093/llc/fqu047},
  pages     = {30 -- 54},
  year      = {2016},
  abstract  = {We use text classification to distinguish automatically between original and translated texts in Hebrew, a morphologically complex language. To this end, we design several linguistically informed feature sets that capture word-level and sub-word-level (in particular, morphological) properties of Hebrew. Such features are abstract enough to allow for the development of accurate, robust classifiers, and they also lend themselves to linguistic interpretation. Careful evaluation shows that some of the classifiers we define are, indeed, highly accurate, and scale up nicely to domains that they were not trained on. In addition, analysis of the best features provides insight into the morphological properties of translated texts.},
  language  = {en}
}