A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects

Yonatan Belinkov, James Glass


Abstract
Discriminating between closely-related language varieties is considered a challenging and important task. This paper describes our submission to the DSL 2016 shared-task, which included two sub-tasks: one on discriminating similar languages and one on identifying Arabic dialects. We developed a character-level neural network for this task. Given a sequence of characters, our model embeds each character in vector space, runs the sequence through multiple convolutions with different filter widths, and pools the convolutional representations to obtain a hidden vector representation of the text that is used for predicting the language or dialect. We primarily focused on the Arabic dialect identification task and obtained an F1 score of 0.4834, ranking 6th out of 18 participants. We also analyze errors made by our system on the Arabic data in some detail, and point to challenges such an approach is faced with.
Anthology ID:
W16-4819
Volume:
Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Preslav Nakov, Marcos Zampieri, Liling Tan, Nikola Ljubešić, Jörg Tiedemann, Shervin Malmasi
Venue:
VarDial
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
145–152
Language:
URL:
https://aclanthology.org/W16-4819
DOI:
Bibkey:
Cite (ACL):
Yonatan Belinkov and James Glass. 2016. A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects. In Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3), pages 145–152, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects (Belinkov & Glass, VarDial 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-4819.pdf
Code
 boknilev/dsl-char-cnn