Skip to content
conftrace_
2018 COLING COLING 2018

HeLI-based Experiments in Discriminating Between Dutch and Flemish Subtitles

Abstract

AbstractThis paper presents the experiments and results obtained by the SUKI team in the Discriminating between Dutch and Flemish in Subtitles shared task of the VarDial 2018 Evaluation Campaign. Our best submission was ranked 8th, obtaining macro F1-score of 0.61. Our best results were produced by a language identifier implementing the HeLI method without any modifications. We describe, in addition to the best method we used, some of the experiments we did with unsupervised clustering.

🐣 Hot Topic Early Bird - dialect identification

Authors

Tommi Jauhiainen, Heidi Jauhiainen, Krister Lindén

Topics

Machine Learning > Core Methods > Classification

Keywords

text classification language identification dialect identification
Download PDF

More from COLING 2018

All COLING 2018 papers →
Paraphrastic Variance between European and Brazilian Portuguese
Character Level Convolutional Neural Network for Arabic Dialect Identification
Neural Network Architectures for Arabic Dialect Identification
Measuring language distance among historical varieties using perplexity. Application to European Portuguese.
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