Advertisement

Deep Convolutional Networks for Supervised Morpheme Segmentation of Russian Language

  • Alexey Sorokin
  • Anastasia Kravtsova
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 930)

Abstract

The present paper addresses the task of morphological segmentation for Russian language. We show that deep convolutional neural networks solve this problem with F1-score of 98% over morpheme boundaries and beat existing non-neural approaches.

Keywords

Morpheme segmentation Neural networks Evaluation 

References

  1. 1.
    Botha, J., Blunsom, P.: Compositional morphology for word representations and language modelling. In: International Conference on Machine Learning, pp. 1899–1907 (2014)Google Scholar
  2. 2.
    Creutz, M., Lagus, K.: Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0. Helsinki University of Technology, Helsinki (2005)Google Scholar
  3. 3.
    Harris, Z.S.: Morpheme boundaries within words: report on a computer test. In: Harris, Z.S. (ed.) Papers in Structural and Transformational Linguistics. FLIS, pp. 68–77. Springer, Dordrecht (1970).  https://doi.org/10.1007/978-94-017-6059-1_3CrossRefzbMATHGoogle Scholar
  4. 4.
    Ruokolainen, T., et al.: Painless semi-supervised morphological segmentation using conditional random fields. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, vol. 2: Short Papers, pp. 84–89 (2014)Google Scholar
  5. 5.
    Ruzsics, T., Samardzic, T.: Neural sequence-to-sequence learning of internal word structure. In: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pp. 184–194 (2017)Google Scholar
  6. 6.
    Sirts, K., Goldwater, S.: Minimally-supervised morphological segmentation using adaptor grammars. Trans. Assoc. Comput. Linguist. T. 1, 255–266 (2013)Google Scholar
  7. 7.
    Shao, Y.: Cross-lingual word segmentation and morpheme segmentation as sequence labelling. arXiv preprint arXiv:1709.03756 (2017)
  8. 8.
    Tikhonov, A.N.: Morphemno-orfograficheskij slovar, 704 c. ACT Publishing (2002). (in Russian)Google Scholar
  9. 9.
    Vylomova, E., et al.: Word representation models for morphologically rich languages in neural machine translation. arXiv preprint arXiv:1606.04217 (2016)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Faculty of Mechanics and MathematicsLomonosov Moscow State UniversityMoscowRussia
  2. 2.Moscow Institute of Physics and TechnologyMoscowRussia

Personalised recommendations