conftrace_

2018 COLING COLING 2018

Discriminating between Indo-Aryan Languages Using SVM Ensembles

Abstract

AbstractIn 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. 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.

Authors

Alina Maria Ciobanu, Marcos Zampieri, Shervin Malmasi, Santanu Pal, Liviu P. Dinu

Topics

Artificial Intelligence > Core AI > Multi-Agent Systems

Keywords

language identification word features support vector machine ensemble method indo-aryan language character feature

More from COLING 2018

All COLING 2018 papers →

Comparing CRF and LSTM performance on the task of morphosyntactic tagging of non-standard varieties of South Slavic languages

Computationally efficient discrimination between language varieties with large feature vectors and regularized classifiers

Character Level Convolutional Neural Network for German Dialect Identification

IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018

Exploring Classifier Combinations for Language Variety Identification

Identification of Differences between Dutch Language Varieties with the VarDial2018 Dutch-Flemish Subtitle Data