Discriminating similar languages with token-based backoff
Tommi Jauhiainen, Heidi Jauhiainen, Krister Lindén · Työväentutkimus Vuosikirja · 2015
In this paper we describe the language identification system built within the Finno-Ugric Languages and the Internet project for the Discriminating between Similar Languages (DSL) shared task in LT4VarDial workshop at RANLP-2015. The system reached fourth place in normal closed submissions (94.7% accuracy) and second place in closed submissions with the named entities blinded (93.0% accuracy).