Teodor Vuºcan, Emma Tamâianu, Sanda Cherata * SILEX - a Lexico-Morphological Software for Romanian



5. Applications of SILEX

The automatic processing of Romanian texts cannot be performed without a tool like SILEX. Its functions, as well as the applications that SILEX make possible, are of theoretic-descriptive relevance, as well as of practical importance.

Here are some of these applications, in the decreasing order of their functional complexity.

  1. orthographic and morphological machine dictionary for Romanian, easy to maintain and to enrich, available in both printable and electronic form;
  2. machine dictionary of homograph forms for the Romaian language, available in both printable and electronic form;
  3. spelling-checker for Romanian texts;
  4. system for statistical studies on the Romanian vocabulary, on various criteria and criteria combinations;
  5. support to any kind of synchronic (and, in the future, for diachronic) research on the Romanian language; (some examples of such research objectives are: productivity of some derivation procedures, the relative occurrence of various types of paradigms);
  6. system for lexical and grammatical statistic studies on Romanian literary texts;
  7. system for concordances of Romanian literary texts, lemmatization being automatically performed (in most of the cases);
  8. educational support for computer-aided study of Romanian grammar, in secondary education and in teaching Romanian as a foreign language (orthography, morphology and vocabulary).

6. Considerations on SILEX implementation and efficiency

SILEX is implemented under the FoxPro 2.7 database system, on a IBM PC-compatible computer. It performs about 1100 anayses per minute on a computer with 4MB RAM and about 2200 analyses per minute on a computer with 8MB RAM. A Romanian spelling-checker is in an advanced stage of development. SILEX was used to spelling-check several issues of Echinox and it proved to be useful and effective.

The use of the lemmatization function of SILEX in the CONCORD system, for generating concordances of Romanian poetic texts, proved its functionality and efficiency.

New directions of research are meant to extend the morphological analysis function by taking into account the left-context of the analyzed word. In this way, the problem of analytical word inflected forms will also be successfully solved.

References

  1. *** Gramatica limbii române, Edit.Academiei, Bucureºti, 1966.
  2. *** Dictionar ortografic, ortoepic ºi morfologic al limbii române, Edit. Academiei, 1982.
  3. *** COLING BUDAPEST, Proceedings of the 12th International Conference on Computational Linguistics,1988.
  4. *** Dicþionar ortografic cu elemente de ortoepie ºi morfologie, Redacþia principalã a Enciclopediei Sovietice Moldoveneºti, Chiºinãu, 1991.
  5. *** Indreptar ortografic, ortoepic ºi de punctuaþie, Edit. Academiei, 1996.
  6. BIEN, J.S., Toward computerized dictionaries for inflexional languages internal design philosophy, in Machine Translation, Cambridge University Press, 1987.
  7. BREBAN, V., Dicþionar general al limbii române, Edit. Enciclopedicã, 1992.
  8. CHERATA, SANDA, Sistem de realizare a concordanþelor limbii poetice româneºti, în D. Tufiº (ed.), Limbaj ºi Tehnologie, Edit. Academiei Române, 1996, pp. 215-220.
  9. CHERATA, SANDA, VUªCAN, T., TAMÂIANU, E., SILEX -Un sistem lexico-morfologic computerizat pentru analiza textelor româneºti, Dacoromania, Nr. 1, 1996 (forthcoming).
  10. CHERATA, SANDA, VUªCAN, T., TAMÂIANU E., SILEX - Funcþiile de lematizare ºi de generare a paradigmelor, Dacoromania, Nr. 2, 1996 (forthcoming).
  11. COTEANU, I., Gramatica de bazã a limbii române, Edit. Albatros, 1982.
  12. DIMITRIU, C., Gramatica limbii române explicatã - Morfologia, Edit. Junimea, 1979.
  13. GUÞU-ROMALO, VALERIA, Morfologia structuralã a limbii române (substantiv, adjectiv, verb), Edit. Academiei, Bucureºti, 1968.
  14. IRIMIA , D., Structura gramaticalã a limbii române. VERBUL, Edit. Junimea, 1976.
  15. IORDAN, I., ROBU, V, Limba românã contemporanã, Edit. Didacticã si Pedagogicã, 1978.
  16. KAY, M., The Dictionary of the Future and the Future of the Dictionary, in Machine Translation, Cambridge University Press, 1987.
  17. LYONS, J., Introducere în lingvistica teoreticã, Edit. ªiinþificã, Bucureºti, 1995.
  18. MANOLIU, MARIA, Morfemul în lingvistica modernã, Limba românã, XII, nr. 1, Bucureºti, 1963.
  19. MARCU, F., MANECA, C., Dicþionar de neologisme, Edit. Academiei, 1978.
  20. MOISIL, Gr., Problèmes posés par la traduction automatique. Le declinaison en roumain écrit, Cahiers de linguistique thèorique et appliqué, II, Bucarest, 1962.
  21. ªUTEU, F., Dicþionar ortografic al limbii române, Edit. Floarea Darurilor, Bucureºti, 1995, Edit. I.O.
  22. ULLMAN, J.D., Principles of Databases System, Computer Science Press, 1982.
  23. ZAMPOLLI, A., Lexicological and Lexicographical Activities at the Istituto di Lingvistica, Lingvistica Computazionale, 1983/3.


67

Previous Index Next