Abstract
In order to improve the performance of a deep-learning neural network, the paper outlines a stack-based approach incorporating various information sources. A named entity recognition system for Amharic was implemented using a recurrent neural network, a bi-directional long short term memory model. Word vectors based on semantic information were built using an unsupervised learning algorithm, word2vec, while a Conditional Random Fields (CRF) classifier was trained on language independent features to predict each token’s named entity class. The predictions, features and word vectors were fed to the deep neural network to assign labels to the words. This stack-based approach reached an 74.26% F-score, outperforming various other deep-learning set-ups, as well as a baseline CRF classifier, and an ensemble method incorporating the same information sources.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The CIA World Factbook estimates Ethiopia’s population to currently be 102.4 million, with 27% having Amharic as first language (https://www.cia.gov/library/publications/the-world-factbook/geos/et.html), while Hudson [12] claimed Amharic to be understood by about 40% of the Ethiopians—at least at that time.
- 2.
- 3.
- 4.
- 5.
References
Al-Rfou, R., Kulkarni, V., Perozzi, B., Skiena, S.: POLYGLOT-NER: massive multilingual named entity recognition. In: Proceedings of the 2015 SIAM International Conference on Data Mining (SDM 2015). Society for Industrial and Applied Mathematics, Vancouver, June 2015
Al-Rfou, R., Perozzi, B., Skiena, S.: Polyglot: Distributed word representations for multilingual NLP. In: Proceedings of the 17th Conference on Computational Natural Language Learning (CONLL 2013), pp. 586–594. ACL, Sofia, August 2013
Alemu, B.: A named entity recognition for Amharic. Master’s thesis, School of Information Science, Addis Ababa University, Addis Ababa, Ethiopia, June 2013
Belay, M.T.: Amharic named entity recognition using a hybrid approach. Master’s thesis, School of Information Science, Addis Ababa University, Addis Ababa, Ethiopia, August 2014
Chiu, J.P.C., Nichols, E.: Named entity recognition with bidirectional LSTM-CNNs. Trans. ACL 4, 357–370 (2016)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)
Demeke, G.A., Getachew, M.: Manual annotation of Amharic news items with part-of-speech tags and its challenges. ELRC Working Papers, vol. 2(1), pp. 1–17, March 2006
Gambäck, B.: Tagging and verifying an Amharic news corpus. In: Proceedings of the 8th International Conference on Language Resources and Evaluation, pp. 79–84. ELRA, Istanbul, May 2012. Workshop on Language Technology for Normalisation of Less-Resourced Languages
Gambäck, B., Asker, L.: Experiences with developing language processing tools and corpora for Amharic. In: Cunningham, P., Cunningham, M. (eds.) Proceedings of IST-Africa 2010, the 5th Conference on Regional Impact of Information Society Technologies in Africa. IIMC, Durban, May 2010
Gasser, M.: HornMorpho: a system for morphological processing of Amharic, Oromo, and Tigrinya. In: Proceedings of Conference on Human Language Technology for Development, Alexandria, Egypt, pp. 94–99, May 2011
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. CoRR abs/1508.01991 (2015)
Hudson, G.: Linguistic analysis of the 1994 Ethiopian census. Northeast Afr. Stud. 6(3), 89–107 (1999)
Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning, ICML 2001, pp. 282–289. Morgan Kaufmann Publishers Inc., San Francisco (2001)
Mehamed, M.A.: Named entity recognition for Amharic language. Master’s thesis, Department of Computer Science, Addis Ababa University, Addis Ababa, Ethiopia, November 2010
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs/1301.3781 (2013)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems 26 (NIPS 2013), pp. 3111–3119. Curran Associates, Red Hook (2013)
Poostchi, H., Borzeshi, E.Z., Abdous, M., Piccardi, M.: PersoNER: persian named-entity recognition. In: Proceedings of the 26th International Conference on Computational Linguistics, pp. 3381–3389. ACL, Osaka, December 2016
Rong, X.: word2vec parameter learning explained. CoRR abs/1411.2738 (2014)
Takeuchi, K., Collier, N.: Use of support vector machines in extended named entity recognition. In: Proceedings of the 6th Conference on Natural Language Learning. COLING-2002, vol. 20, pp. 1–7. Association for Computational Linguistics, Stroudsburg (2002)
Zhou, G., Su, J.: Named entity recognition using an HMM-based chunk tagger. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, ACL 2002, pp. 473–480. Association for Computational Linguistics, Stroudsburg (2002)
Acknowledgements
Thanks to Lars Bungum, Biswanath Barik, the anonymous reviewers, and our project partners at Masaryk University (Brno, Czech Republic), Addis Ababa University (Ethiopia), and University of Oslo (Norway). This work was carried out within the HaBiT project (“Harvesting big text data for under-resourced languages”: http://www.habit-project.eu) funded by the Research Council of Norway (NFR) and the Czech Ministry of Education, Youth and Sports (MŠMT) through the CZ09 Czech-Norwegian Research Programme and the EEA/Norway Financial Mechanism under Project Contract 7F14047.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Sikdar, U.K., Gambäck, B. (2018). Named Entity Recognition for Amharic Using Stack-Based Deep Learning. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2017. Lecture Notes in Computer Science(), vol 10761. Springer, Cham. https://doi.org/10.1007/978-3-319-77113-7_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-77113-7_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77112-0
Online ISBN: 978-3-319-77113-7
eBook Packages: Computer ScienceComputer Science (R0)