A Hybrid Approach for Arabic Diacritization
The orthography of Modern standard Arabic (MSA) includes a set of special marks called diacritics that carry the intended pronunciation of words. Arabic text is usually written without diacritics which leads to major linguistic ambiguities in most of the cases since Arabic words have different meaning depending on how they are diactritized. This paper introduces a hybrid diacritization system combining both rule-based and data- driven techniques targeting standard Arabic text. Our system relies on automatic correction, morphological analysis, part of speech tagging and out of vocabulary diacritization components. The system shows improved results over the best reported systems in terms of full-form diacritization, and comparable results on the level of morphological diacritization. We report these results by evaluating our system using the same training and evaluation sets used by the systems we compare against.. Our system shows a word error rate (WER) of 4.4% on the morphological diacritization, ignoring the last letter diacritics, and 11.4% on the full-form diacritization including case ending diacritics. This means an absolute 1.1% reduction on the word error rate (WER) over the best reported system.
KeywordsArabic Arabic orthography diacritization vowelization morphology morphology features morphological analysis part-of-speech tagging automatic correction Viterbi case ending natural language processing language modeling conditional random fields CRF
Unable to display preview. Download preview PDF.
- 2.Habash, N., Rambow, O.: Arabic diacritization through full morphological tagging. In: NAACL-Short 2007 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers, pp. 53–56 (2007)Google Scholar
- 3.Zitouni, I., Sorensen, J.S., Sarikaya, R.: Maximum entropy based restoration of arabic diacritics. In: Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pp. 577–584 (2006)Google Scholar
- 4.Habash, N., Rambow, O.: Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL 2005, pp. 573–580 (2005)Google Scholar
- 5.Buckwalter, T.: Issues in Arabic orthography and morphology analysis. In: Proceedings of the COLING 2004 Workshop on Computational Approaches to Arabic Script-Based Languages, pp. 31–34 (2004)Google Scholar
- 6.Emam, O., Fisher, V.: A hierarchical approach for the statistical vowelization of arabic text. Tech. rep., IBM (2004)Google Scholar
- 7.Gimnez, J., Mrquez, L.: Svmtool: A general pos tagging generator based on support vector machines. In: LERC 2004. pp. 573–580 (2004)Google Scholar
- 8.Maamouri, M., Bies, A., Buckwalter, T., Mekki, W.: The penn arabic treebank: Building a large-scale annotated arabic corpus. In: Arabic Lang. Technol. Resources Int. Conf.; NEMLAR, Cairo, Egypt (2004) Google Scholar
- 9.Stolcke, A.: Srilman extensible language modeling toolkit. In: Proceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), pp. 901–904 (2002)Google Scholar
- 10.Laerty, J.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: The Eighteenth International Conference on Machine Learning, pp. 282–289 (2001)Google Scholar
- 11.Jurafsky, D., Martin, J.H.: Speech and Language Processing; an Introduction to Natural Language Processing, Computational Linguistics, and Speech Processing. Prentice-Hall (2000)Google Scholar