Abstract
In this paper, we introduce a neural network based sequence learning approach for the task of Arabic dialect classification. Character models based on recurrent neural networks with Long Short-Term Memory (LSTM) are suggested to classify short texts, such as tweets, written in different Arabic dialects. The LSTM-based character models can handle long-term dependencies in character sequences and do not require a set of linguistic rules at word-level, which is especially useful for the rich morphology of the Arabic language and the lack of strict orthographic rules for dialects. On the Tunisian Election Twitter dataset, our system achieves a promising average accuracy of 92.2% for distinguishing Modern Standard Arabic from Tunisian dialect. On the Multidialectal Parallel Corpus of Arabic, the proposed character models can distinguish six classes, Modern Standard Arabic and five Arabic dialects, with an average accuracy of 63.4%. They clearly outperform a standard word-level approach based on statistical n-grams as well as several other existing systems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Younes, J., Achour, H., Souissi, E.: Constructing linguistic resources for the Tunisian dialect using textual user-generated contents on the social web. LNCS, pp. 3–14. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24800-4_1
Sayadi, K., Liwicki, M., Ingold, R., Bui, M.: Tunisian dialect and modern standard Arabic dataset for sentiment analysis: Tunisian election context. In: ACLing (2016)
Hermans, M., Schrauwen, B.: Training and analysing deep recurrent neural networks. In Burges, C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 26, pp. 190–198 (2013)
Karpathy, A., Johnson, J., Fei-Fei, L.: Visualizing and understanding recurrent networks (2015). arXiv:1506.02078
Elfardy, H., Diab, M.T.: Sentence level dialect identification in Arabic. In: ACL (2013)
Zaidan, O.F., Callison-Burch, C.: Arabic dialect identification. Comput. Linguist. 40, 171–202 (2014)
Malmasi, S., Refaee, E., Dras, M.: Arabic dialect identification using a parallel multidialectal corpus. In: Proceedings of the 14th Conference of the Pacific Association for Computational Linguistics (PACLING 2015), Bali, Indonesia (2015)
Bouamor, H., Habash, N., Oflazer, K.: A multidialectal parallel corpus of Arabic. In: LREC (2014)
Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649–657 (2015)
Kim, Y., Jernite, Y., Sontag, D., Rush, A.M.: Character-aware neural language models. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. AAAI (2016)
Xiao, Y., Cho, K.: Efficient character-level document classification by combining convolution and recurrent layers (2016). arXiv:1602.00367
Zhang, X., LeCun, Y.: Text understanding from scratch (2015). arXiv:1502.01710
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: ICML (1997)
Kim, Y.: Convolutional Neural Networks for Sentence Classification. In: EMNLP (2014)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). abs/1301.3781
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. EMNLP 14, 1532–1543 (2014)
Dauphin, Y.N., Vries, H.d., Bengio, Y.: Equilibrated adaptive learning rates for non-convex optimization. In: Proceedings of the 28th International Conference on Neural Information Processing Systems. NIPS’15, pp. 1504–1512. MIT Press, Cambridge, MA, USA (2015)
Darwish, K., Sajjad, H., Mubarak, H.: Verifiably effective Arabic dialect identification. In: EMNLP, pp. 1465–1468 (2014)
Adouane, W., Semmar, N., Johansson, R., Bobicev, V.: Automatic detection of arabicized berber and arabic varieties. VarDial 3, 63 (2016)
Graves, A., Liwicki, M., Fernndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31, 855–868 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Speed Test
A Speed Test
In order to get an idea about the speed of processing the text records (e.g. tweets) provided by the described environment based on Torch, we illustrate in the Fig. 3 the processing time per second and per tweet during the training phase.
Hardware comparison concerning training time
We compared the polyGPU configuration with the macCPU configuration consists of a MacBook Air 4.2 CPU of a with a 1.7 GHz Intel Core i5 processor and 4GB of DDR3 RAM at 1333 MHz. and he monoGPU configuration consists of a single NVIDIA Corporation GK107 [GeForce GT 740] GPU deployed in a PC with CUDA Cores: 384 a VRAM: 2 GB DDR3 and Memory Clock at 1.8 Gbps.
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Sayadi, K., Hamidi, M., Bui, M., Liwicki, M., Fischer, A. (2018). Character-Level Dialect Identification in Arabic Using Long Short-Term Memory. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2017. Lecture Notes in Computer Science(), vol 10762. Springer, Cham. https://doi.org/10.1007/978-3-319-77116-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-77116-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77115-1
Online ISBN: 978-3-319-77116-8
eBook Packages: Computer ScienceComputer Science (R0)