Byte-based Language Identification with Deep Convolutional Networks
Computation and Language
2016-10-31 v2
Abstract
We report on our system for the shared task on discriminating between similar languages (DSL 2016). The system uses only byte representations in a deep residual network (ResNet). The system, named ResIdent, is trained only on the data released with the task (closed training). We obtain 84.88% accuracy on subtask A, 68.80% accuracy on subtask B1, and 69.80% accuracy on subtask B2. A large difference in accuracy on development data can be observed with relatively minor changes in our network's architecture and hyperparameters. We therefore expect fine-tuning of these parameters to yield higher accuracies.
Cite
@article{arxiv.1609.09004,
title = {Byte-based Language Identification with Deep Convolutional Networks},
author = {Johannes Bjerva},
journal= {arXiv preprint arXiv:1609.09004},
year = {2016}
}
Comments
7 pages. Adapted reviewer comments. arXiv admin note: text overlap with arXiv:1609.07053