Discriminating between Indo-Aryan Languages Using SVM Ensembles
This work addresses language identification for specific Indo-Aryan languages, but it is incremental as it applies existing methods to a new dataset.
The paper tackled the problem of discriminating between five similar Indo-Aryan languages using SVM ensembles, achieving an 88.95% F1 score and ranking 3rd out of 8 teams in a shared task.
In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. We investigate the performance of individual features and combine the output of single classifiers to maximize performance. The system competed in the Indo-Aryan Language Identification (ILI) shared task organized within the VarDial Evaluation Campaign 2018. Our best entry in the competition, named ILIdentification, scored 88:95% F1 score and it was ranked 3rd out of 8 teams.