Sari la conținut

Article on Google Translate for Romanian is out!

Our paper, How much Romanian does Google Translate know? A corpus-informed genre-specific error analysis of English-into-Romanian translations, waspublished in Studies about Languages.

It is one of the few publications which presents research results concerning translation challenges for Romanian-English Google Translate samples.

Examples of such translation challenges:

In the lexico-semantic category:

  • incorrect choice of equivalents both for monosemantic and for polysemantic words;
  • incorrect choice of equivalents for words with a metaphorical/ euphemistic meaning;
  • incorrect choice of equivalents for domain-specific terms;
  • incorrect (direct) translation of idiomatic phrases;
  • incorrect interpretation of geographical varieties of English;
  • incorrect interpretation of neologisms;
  • incorrect choice of register.

In the morphological-syntactic category:

  • incorrect agreement in number, gender and case;
  • random gender assignment;
  • incorrect inflection and conjugation;
  • misinterpretation of features of certain morphological categories;
  • misinterpretation of phrase structure.

Spelling errors were rarely encountered in the Romanian texts. They mainly consist of:

  • misspelling of words;
  • incorrect use of the hyphen


Lasă un răspuns

Adresa ta de email nu va fi publicată. Câmpurile obligatorii sunt marcate cu *