Abstract
Morphological inflection (MI) is the task of generating a target word form based on a source word and a set of target morphological tags. We present different language-agnostic systems for MI and report results on datasets of three different sizes: low, medium and high. All these systems are deep neural network based. We implement and describe a lower baseline, and show that our systems improve on this baseline, as well as meet the state-of-art. One significant contribution through this work is studying the different neural architectures that perform best on different dataset sizes as well as on different languages. Another contribution is exploring the use of phonological features of the language in addition to characters, as well as pre-training of word embeddings. We also implement a hybrid system which combines rules learnt from string alignments along with deep learning. The significance of our work lies in the fact that the systems presented can be used for any language (we present results on 52 languages we experimented with) and in our analysis of how linguistic properties of each language has a strong bearing on the design of the neural architecture used for that language.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Minkov, E., Toutanova, K., Suzuki, H.: Generating complex morphology for machine translation. In: ACL, vol. 7, pp. 128–135 (2007)
Chahuneau, V., Smith, N.A., Dyer, C.: Knowledge-rich morphological priors for Bayesian language models. In: Association for Computational Linguistics (2013)
Oflazer, K., Say, B., et al.: Integrating morphology with multi-word expression processing in Turkish. In: Proceedings of the Workshop on Multiword Expressions: Integrating Processing, pp. 64–71. Association for Computational Linguistics (2004)
Sudhakar, A., Singh, A.K.: Experiments on morphological reinflection: Conll-2017 shared task. In: Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, pp. 71–78 (2017)
Durrett, G., DeNero, J.: Supervised learning of complete morphological paradigms. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, Georgia, pp. 1185–1195, June 2013
Ahlberg, M., Forsberg, M., Hulden, M.: Semi-supervised learning of morphological paradigms and lexicons. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics: Language Technology (Computational Linguistics), Gothenburg, Sweden, pp. 569–578, April 2014
Ahlberg, M., Forsberg, M., Hulden, M.: Paradigm classification in supervised learning of morphology. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Denver, Colorado, pp. 1024–1029, June 2015
Faruqui, M., Tsvetkov, Y., Neubig, G., Dyer, C.: Morphological inflection generation using character sequence to sequence learning. In: Proceedings of NAACL (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014)
Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 437–478. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_26
Cho, K., van Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of EMNLP 2014 (2014)
Cotterell, R., et al.: The CoNLL-SIGMORPHON 2017 shared task: Universal morphological reinflection in 52 languages. In: Proceedings of the CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, Vancouver, Canada. Association for Computational Linguistics, August 2017
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, vol. 14, pp. 1532–1543 (2014)
Singh, A.K.: Digitizing the Legacy of Indian Languages. ICFAI Books, Hyderabad (2009)
Cotterell, R., Kirov, C., Sylak-Glassman, J., Yarowsky, D., Eisner, J., Hulden, M.: The sigmorphon 2016 shared task-morphological reinflection. In: Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pp. 10–22 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Sudhakar, A., Mundotiya, R.K., Singh, A.K. (2023). Experiments on Deep Morphological Inflection. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2018. Lecture Notes in Computer Science, vol 13396. Springer, Cham. https://doi.org/10.1007/978-3-031-23793-5_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-23793-5_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23792-8
Online ISBN: 978-3-031-23793-5
eBook Packages: Computer ScienceComputer Science (R0)