Using Cognates in a French-Romanian Lexical Alignment System: A Comparative Study
Mirabela Navlea, Amalia Todiraşcu · 2011
This paper describes a hybrid French- Romanian cognate identification module. This module is used by a lexical alignment system. Our cognate identification method uses lemmatized, tagged and sentence-aligned parallel corpora. This method combines statistical techniques, linguistic information (lemmas, POS tags) and orthographic adjustments. We evaluate our cognate identification module and we compare it to other methods using pure statistical techniques. Thus, we study the impact of the used linguistic information and the orthographic adjustments on the results of the cognate identification module and on cognate alignment. Our method obtains the best results in comparison with the other implemented statistical methods. 1