Design and Evaluation of a Versatile Architecture for a Multilingual Word Prediction System

  • Sira E. Palazuelos-Cagigas
  • José L. Martín-Sánchez
  • Lisset Hierrezuelo Sabatela
  • Javier Macías Guarasa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4061)


Word prediction is a process that tries to guess the word a user is writing, at the same time he/she is doing it. It is mainly used to decrease the effort needed to write a text in applications devoted to people with disabilities. In this paper, we describe and evaluate the architecture of a multilingual word prediction system. The proposed architecture is modular and flexible, with common interfaces between the modules to allow the use of different prediction algorithms or even the prediction in different languages. The current system consists of a general lexicon for each language, the possibility to create and store personal lexicons, prediction methods based on words and POS (parts of speech) probabilistic grammars (when available). The system has been trained and evaluated for English, Portuguese, Spanish and Swedish. The Spanish version is currently included in a technical aid widely used for people with communication disabilities.


Prediction Method Prediction Process General Lexicon Spelling Mistake Word Suffix 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Langley, P.: Machine Learning for Adaptive User Interfaces. In: Proceedings of the 21st German Annual Conference on Artificial Intelligence, Freiburg. Alemania, pp. 53–62. Springer, Heidelberg (1997), Google Scholar
  2. 2.
    Allen, J.: Natural language Understanding, 2nd edn. Benjamin/Cummings Publishing Company Inc. (1994)Google Scholar
  3. 3.
    Palazuelos, S.: Aportación a la predicción de palabras en castellano y su integración en sistemas de ayuda a personas con discapacidad física. Tesis Doctoral (2001)Google Scholar
  4. 4.
    Hierrezuelo, L., Palazuelos, S.: Revisión y propuesta de sistemas de ayuda a la escritura para personas con discapacidad física. In: Congreso TELEC 2004, Santiago de Cuba (2004)Google Scholar
  5. 5.
    Moulton, B., Lesher, G., Higginbotham, J.: A system for automatic abbreviated expansion (1999),
  6. 6.
    Demasco, P., McCoy, K.F., Jones, M., Pennington, C., Snyder, S.: Compansion: A technique that applies natural language processing to augmentative communication. Rehabilitation R & D Progress Reports / Journal of Rehabilitation Research and Development 29, 180–181 (1991)Google Scholar
  7. 7.
    Karttunen, L.: Applications of Finite-State Transducers in Natural-Language Processing,
  8. 8.
    Earley, J.: An Eficient Context-Free Parsing Algorithm. Comm. of the ACM 13(2), 94–102 (1970)zbMATHCrossRefGoogle Scholar
  9. 9.
    Palazuelos, S.E., Aguilera, S., Rodrigo, J.L., Godino, J., Martín, J.: Considerations on the Automatic Evaluation of word prediction systems. In: Augmentative and Alternative Communication: New Directions in Research and Practice, pp. 92–104. Whurr Publishers, London (1999)Google Scholar
  10. 10.
    Carlberger, A., Carlberger, J., Magnuson, T., Palazuelos, S., Hunnicutt, S., Aguilera, S.: Profet, a New Generation of Word Prediction: an Evaluation Study. In: Workshop on NLP for Communication Aids, ACL/EACL 1997. Madrid, España. In: Proceedings de Workshop on NLP for Communication Aids. ACL/EACL 1997. 1-908-873-3898. Ed. Assotiation for Computational Linguistics, Madrid, España, pp. 23–28 (1997)Google Scholar
  11. 11.
    Palazuelos, S., Martín, J., Arenas, J., Godino, J., Aguilera, S.: Communication strategies using PredWin for people with disabilities. In: Conference and Workshop on Assistive Technology for Vision and Hearing Impaired, Castelvecchio Pascoli, Italia (2001)Google Scholar
  12. 12.
    Fazly, A., Hirst, G.: Testing the Efficacy of Part-of-speech Information in Word Completion. In: 10th EACL, Proceeding of the Workshop on Language Modeling for Text Entry Methods, Budapest (Hungary) (2003)Google Scholar
  13. 13.
    Ebba, G., Eva, P.: A Swedish Grammar for Word Prediction
  14. 14.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sira E. Palazuelos-Cagigas
    • 1
  • José L. Martín-Sánchez
    • 1
  • Lisset Hierrezuelo Sabatela
    • 1
  • Javier Macías Guarasa
    • 2
  1. 1.Department of Electronics, Polytechnic SchoolUniversity of AlcaláAlcalá de HenaresSpain
  2. 2.Speech Technology Group, Department of Electronics Engineering, E.T.S.I. de TelecomunicaciónUniversidad Politécnica de Madrid 

Personalised recommendations