Lexical Analysis of Serbian with Conditional Random Fields and Large-Coverage Finite-State Resources

  • Mathieu ConstantEmail author
  • Cvetana Krstev
  • Duško Vitas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10930)


This article describes a joint approach to lexical tagging in Serbian, combining three fundamental natural language processing tasks: part-of-speech tagging, compound and named entity recognition. The proposed system relies on conditional random fields that are trained from a newly released annotated corpus and finite-state lexical resources used in an existing symbolic Serbian tagging system. Experimental results show that a joint strategy is more robust than pipeline ones and that the use of lexical resources has a significant positive impact on tagging, in particular on out-of-domain texts.



This research was partly supported by the Serbian Ministry of Education and Science under grant #47003 and by the French National Research Agency (ANR) through the project PARSEME-FR (ANR-14-CERA-0001).


  1. 1.
    Agić, v., Ljubešić, N., Merkler, D.: Lemmatization and Morphosyntactic Tagging of Croatian and Serbian. In: Proceedings of the 4th Biennial International Workshop on Balto-Slavic Natural Language Processing, pp. 48–57. Association for Computational Linguistics, Sofia, Bulgaria, August 2013Google Scholar
  2. 2.
    Blunsom, P., Baldwin, T.: Multilingual Deep Lexical Acquisition for HPSGs via Supertagging. In: Proceedings of EMNLP 2006, Sydney, pp. 164–171 (2006)Google Scholar
  3. 3.
    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)zbMATHGoogle Scholar
  4. 4.
    Constant, M., Sigogne, A.: MWU-aware part-of-speech tagging with a CRF model and lexical resources. In: Proceedings of the Workshop on Multiword Expressions: from Parsing and Generation to the Real World (MWE 2011), pp. 49–56 (2011)Google Scholar
  5. 5.
    Constant, M., Sigogne, A., Watrin, P.: Discriminative strategies to integrate multiword expression recognition and parsing. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), pp. 204–212 (2012)Google Scholar
  6. 6.
    Constant, M., Tellier, I.: Evaluating the impact of external lexical resources into a CRF-based multiword segmenter and part-of-speech tagger. In: Proceedings of LREC 2012, Istanbul, Turkey (2012)Google Scholar
  7. 7.
    Courtois, B., Silberztein, M.: Dictionnaires électroniques du français. Larousse, Paris (1990)Google Scholar
  8. 8.
    Denis, P., Sagot, B.: Coupling an annotated corpus and a morphosyntactic lexicon for state-of-the-art POS tagging with less human effort. In: Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation (PACLIC 2009), Hong Kong (2009)Google Scholar
  9. 9.
    Finkel, J.R., Manning, C.D.: Joint parsing and named entity recognition. In: Proceedings of the conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2009) (2009)Google Scholar
  10. 10.
    Green, S., de Marneffe, M.C., Bauer, J., Manning, C.D.: Multiword expression identification with tree substitution grammars: a parsing tour de force with French. In: Proceedings of the conference on Empirical Method for Natural Language Processing (EMNLP 2011) (2011)Google Scholar
  11. 11.
    Gross, M.: The use of finite automata in the lexical representation of natural language. In: Gross, M., Perrin, D. (eds.) LITP 1987. LNCS, vol. 377, pp. 34–50. Springer, Heidelberg (1989). Scholar
  12. 12.
    Krstev, C., Obradović, I., Utvić, M., Vitas, D.: A system for named entity recognition based on local grammars. J. Log. Comput. 24(2), 473–489 (2014)CrossRefGoogle Scholar
  13. 13.
    Krstev, C., Vitas, D.: Finate state transducers for recognition and generation of compound words. In: Erjavec, T., Žganec Gros, J. (eds.) Proceedings of the 5th Slovenian and 1st International Conference Language Technologies. pp. 192–197. Institut “Jožef Stefan” (2006)Google Scholar
  14. 14.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random Fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), pp. 282–289 (2001)Google Scholar
  15. 15.
    Legrand, J., Collobert, R.: Phrase representations for multiword expressions. In: Proceedings of the 12th Workshop on Multiword Expressions, pp. 67–71. Association for Computational Linguistics, Berlin, Germany, August 2016Google Scholar
  16. 16.
    Maurel, D., Friburger, N., Antoine, J.Y., Eshkol, I., Nouvel, D., et al.: Cascades de transducteurs autour de la reconnaissance des entités nommées. Traitement Automatique des Langues 52(1), 69–96 (2011)Google Scholar
  17. 17.
    McCallum, A., Li, W.: Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In: Proceedings of the Seventh Conference on Natural Language Learning, CoNLL 2003, Held in cooperation with HLT-NAACL 2003, Edmonton, Canada, May 31 - June 1, 2003, pp. 188–191 (2003)Google Scholar
  18. 18.
    Nivre, J., Nilsson, J.: Multiword units in syntactic parsing. In: Proceedings of Methodologies and Evaluation of Multiword Units in Real-World Applications (MEMURA) (2004)Google Scholar
  19. 19.
    Savary, A., Ramisch, C., Cordeiro, S., Sangati, F., Vincze, V., QasemiZadeh, B., Candito, M., Cap, F., Giouli, V., Stoyanova, I., Doucet, A.: The PARSEME shared task on automatic identification of verbal multiword expressions. In: Proceedings of EACL 2017 Workshop on MWEs, Valencia, pp. 31–47, April 2017Google Scholar
  20. 20.
    Sečujski, M., Delić, V.: A software tool for semi-automatic part-of-speech tagging and sentence accentuation in Serbian language. In: Proceedings of IS-LTC (2006)Google Scholar
  21. 21.
    Shigeto, Y., Azuma, A., Hisamoto, S., Kondo, S., Kouse, T., Sakaguchi, K., Yoshimoto, A., Yung, F., Matsumoto, Y.: Construction of English MWE dictionary and its application to POS tagging. In: Proceedings of the NAACL/HLT Workshop on MWEs, Atlanta, GA, pp. 139–144 (2013)Google Scholar
  22. 22.
    Tjong Kim Sang, E.F., De Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Daelemans, W., Osborne, M. (eds.) Proceedings of CoNLL-2003, Edmonton, Canada, pp. 142–147 (2003)Google Scholar
  23. 23.
    Tufiş, D., Koeva, S., Erjavec, T., Gavrilidou, M., Krstev, C.: Building language resources and translation models for machine translation focused on south slavic and balkan languages. In: Proceedings of the 6th International Conference Formal Approaches to South Slavic and Balkan Languages (FASSBL 2008), Dubrovnik, Croatia, pp. 145–152, September 2008Google Scholar
  24. 24.
    Utvić, M.: Annotating the corpus of contemporary Serbian. INFOtheca 12(2), 36a–47a (2011)Google Scholar
  25. 25.
    Vincze, V., Nagy, I., Berend, G.: Multiword expressions and named entities in the Wiki50 corpus. In: Proceedings of the Conference on Recent Advances in Natural Language Processing (RANLP 2011), pp. 289–295 (2011)Google Scholar
  26. 26.
    Vitas, D., Krstev, C.: Processing of Corpora of Serbian Using Electronic Dictionaries. Prace Filologiczne LXIII, 279–292 (2012)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Mathieu Constant
    • 1
    Email author
  • Cvetana Krstev
    • 2
  • Duško Vitas
    • 2
  1. 1.ATILF UMR 7118Université de Lorraine/CNRSNancyFrance
  2. 2.University of BelgradeBelgradeSerbia

Personalised recommendations