Skip to main content
Springer Nature Link
Log in

Text prediction systems: a survey

  • LONG PAPER
  • Published:
Universal Access in the Information Society Aims and scope Submit manuscript

Abstract

Text prediction is one of the most widely used techniques to enhance the communication rate in augmentative and alternative communication. Prediction systems are traditionally used by people with disabilities (e.g. people with motor and speech impairments). However, new applications, such as writing short text messages via mobile phones, have recently appeared. A vast amount of heterogeneous text prediction methods and techniques can be found in literature. Their heterogeneity makes it difficult to understand and compare them, in order to select the most convenient technique for a specific design. This paper presents a survey on text prediction techniques with the intention to provide a systematic view of this field. Prediction applications and related features, such as block size, dictionary structure, prediction method, user interface, etc., are examined. In addition, prediction measurement parameters and published results are compared. A large number of factors that may influence prediction results, including the acceptance of the system by the users, are reviewed, and their influence on the performance and usability of the system is discussed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. AAC tries to provide ways of communication to people who are not able to speak.

  2. See the monograph [1] for a review of the disabilities that require AAC systems.

  3. In a normal conversation, people can utter about 180–200 words/min, whereas a disabled person using a scanning-based input device can type only 2–10 words/min. This difference may cause practical problems for maintaining a conversation and psychological effects on the users [4].

  4. Standard frequencies from dictionaries are usually taken. If it is possible, it is much better to use the frequencies of the words used by each user. Additionally, there are studies related to the frequencies of the words for different populations, for instance the previously mentioned [12].

  5. In the case of the Basque language, starting from a given root, 62 basic inflections may be obtained. Suffixes may be recursively concatenated (as it is an agglutinated language) increasing the number of possible inflections. With a two-level recursion, it has been estimated that a noun may reach 458,683 variations [3]. Prefixes and infixes are also possible in Basque but it has been found that their frequencies are not very significant comparing to suffixes [29].

References

  1. AAC (1989) Augmentative and alternative communication 5(1)

  2. Abascal J, Gardeazabal L, Garay N (2004) Optimisation of the selection set features for scanning text input. ICCHP 2004, LNCS 3118. Springer, Berlin Heidelberg New York, pp 788–795

    Google Scholar 

  3. Agirre E, Alegria I, Arregi X, Artola X, Diaz De Ilarraza A, Maritxalar M, Sarasola K, Urkia M (1992) Xuxen: a spelling checker/corrector for Basque based on two-level morphology. In: Proceedings of the 3rd conference on applied natural language processing. Association for Computational Linguistics, pp 119–125

  4. Alm N, Arnott JL, Newell A (1989) Discourse analysis and pragmatics in the design of conversation prosthesis. J Med Eng Technol 13(1/2):10–12

    Article  Google Scholar 

  5. Alm N, Newell A, Arnott J (1989) Revolutionary communication system to aid non-speakers. Speech Therapy in Practice Update, pp VII–VIII

  6. Alm N, Arnott JL, Newell AF (1992) Prediction and conversational momentum in an augmentative communication system. Comm ACM 35(5):46–57

    Article  Google Scholar 

  7. Arnott JL, Javed MY (1992) Probabilistic character disambiguation for reduced keyboards using small text simples. Augmentative Alternative Commun 8:215–223

    Article  Google Scholar 

  8. Arruabarrena A, González J (1988) Comunicadores y Emuladores de Teclado. Tecnologías de la Información y Discapacidad. Fundesco, Madrid, pp 133–156

    Google Scholar 

  9. Beattie W, Hine N, Arnott J (1998) Distributed assistive communication devices for non-speaking users. In: Proceedings of the Isaac conference, Dublin (Ireland), pp 447–448

  10. Beck C, Seisenbacher G, Edelmayer G, Zagler W (2004) First user test results with the predictive typing system FASTY. ICCHP 2004, LNCS 3118. Springer, Berlin Heidelberg New York, pp 813–819

    Google Scholar 

  11. Bertenstam J, Hunnicutt S (1995) Adding morphology to a word predictor. In: The European context for assistive technology (Proceedings of the 2nd tide congress). IOS Press/Ohmsa, Bruselas, pp 312–315

  12. Beukelman DR, Yorkston KM, Poblete M, Naranjo C (1984) Frequency of word occurrence in communication samples produced by adult communication aid. J Speech Hear Disord 49:360–367

    Google Scholar 

  13. Boissiere P, Dours D (1996) VITIPI: versatile interpretation of text input by persons with impairments. In: Interdisciplinary aspects on computers helping people with special needs: 5th international conference (ICCHP’96). Oldenbourg, Linz (Austria), pp 165–172

  14. Carlberger J (1997) Design and implementation of a probabilistic word prediction program. Master’s Thesis in Computer Science, Nada, KTH, Stockholm (Sweden). http://www.speech.kth.se/∼Johanc/Thesis/Thesis.doc

  15. Carlberger A, Carlberger J, Magnuson T, Hunnicutt MS, Palazuelos-Cagigas SE, Aguilera Navarro S (1997) Profet, a new generation of word prediction: an evaluation study. In: Proceedings of the natural language processing for communication aids workshop. Association for Computational Linguistics, pp 23–28

  16. Claypool T, Ricketts I, Gregor P, Booth L, Palazuelos S (1998) Learning rates of a tri-gram based gaelic word predictor. In: Proceedings of ISAAC conference, Dublin (Ireland), pp 178–179

  17. Copestake A (1997) Augmented and alternative NLP techniques for augmentative and alternative communication. In: Proceedings of the natural language processing for communication aids workshop. Association for Computational Linguistics, pp 37–42

  18. Copestake A, Flickinger D (1998) Evaluation of NLP technology for AAC using logged data. In: Isaac 98 research symposium proceedings, Whurr Publishers, London. http://www-csli.stanford.edu/∼aac/evaluation-dsp1.htm

  19. Darragh JJ, Witten IH, James ML (1990) The reactive keyboard: a predictive typing aid. Computer 23(11):41–49

    Article  Google Scholar 

  20. Digiovanni JM (1996) Word prediction software as a tool to improve writing literacy. http://san183.sang.wmich.edu/Sped603fall96/Digiovannipaper.html

  21. Even-Zohar Y, Roth D (2000) A Classification approach to word prediction. In: Proceedings of the Naacl’00. http://l2r.cs.uiuc.edu/∼Evenzoha/Papers/Classificationapproach.Ps

  22. Gaiarin M (1999) Un Sistema di Predizione Sintattica per Gnu/Linux. Tesi Di Laurea. Università Degli Studi Di Padova. http://www.dei.unipd.it/∼Gaio/Tesi/Favele.Ps.Gz

  23. Garay N, Abascal J (1994) Using statistical and syntactic information in word prediction for input speed enhancement. Information Systems Design and Hypermedia. Cépaduès-Éditions, Toulouse (France), pp 223–230

    Google Scholar 

  24. Garay-Vitoria N, Abascal J (1994) Application of artificial intelligence methods in a word-prediction aid. ICCHP 1994, LNCS 860. Springer, Berlin Heidelberg New York, pp 363–370

    Google Scholar 

  25. Garay-Vitoria N, Abascal J, Urigoitia-Bengoa S (1995) Application of the human conversation modelling in a telephonic aid. In: Proceedings of the 15th international symposium on human factors in telecommunications (HFT’95), Melbourne (Australia), pp 131–138

  26. Garay-Vitoria N, Abascal J (1997) Intelligent word-prediction to enhance text input rate. In: Proceedings of the intelligent user interfaces 97 congress. ACM Press, New York, pp 241–244

  27. Garay-Vitoria N, Abascal J (1997) Word prediction for inflected languages. Application to Basque language. In: Proceedings of the natural language processing for communication aids workshop. Association for Computational Linguistics, pp 29–36

  28. Garay-Vitoria N (2001) Sistemas de Predicción Lingüística. Aplicación a Idiomas con Alto y Bajo Grado de Flexión, en el Ámbito de la Comunicación Alternativa y Aumentativa. Servicio Editorial de la Universidad del País Vasco, Leioa (Spain). ISBN:84–8373–355–2

  29. Garay N, Abascal J, Gardeazabal L (2002) Evaluation of prediction methods applied to an inflected language. In: Proceedings of the 5th International Conference Text, Speech and Dialogue TSD2002. Springer, Berlin Heidelberg New York, pp 397–403

  30. Garay N, Abascal J (2004) A comparison of prediction techniques to enhance the communication rate. In: Proceedings of the 8th ERCIM workshop, LNCS 3196. Springer, Berlin Heidelberg New York, pp 400–417

  31. Garay-Vitoria N, Abascal J (2004) User interface factors related to word prediction systems. In: Proceedings of the 7th international conference on work with computing Systems WWCS2004. Damai Sciences, Kuala Lumpur (Malaysia), pp 77–82

  32. Gardeazabal L (2000) Aplicaciones de la Tecnología de Computadores a la Mejora de la Velocidad de Comunicación en Sistemas de Comunicación Aumentativa y Alternativa. Servicio Editorial de la Universidad del País Vasco, Leioa (Spain). ISBN:84–8373–301–3

  33. Gillette Y, Hoffman JL (1995) Getting to word prediction: developmental literacy and AAC. In: Proceedings of the 10th annual international conference, technology and persons with disabilities. Northridge, California. Taken From [54]

  34. González Abascal J (1992) Un Método de Compresión de Textos Basado en la Posicionalidad y el Rendimiento. Aplicación al Euskara. Servicio Editorial de la Universidad del País Vasco, Leioa (Spain). ISBN:84–7585–301–3.

  35. Greenberg S, Darragh JJ, Maulsby D, Witten IH (1995) Predictive interfaces: what will they think of next? Extra-ordinary human-computer interaction. Interfaces for users with disabilities, Edwards ADN (Ed) Cambridge University Press, London, pp 103–140

  36. Hecht J, Heinisch B (1997) A comparative overview of word prediction software for Windows 95. http://www.southernct.edu/Departments/Cat/Wordpred.html

  37. Heckathorne CW, Childress DS (1983) Applying anticipatory text selection in a writing aid for people with severe motor impairment. IEEE Micro 3(3):17–23

    Article  Google Scholar 

  38. Heinisch B, Hecht J (1993) Predictive word processors: a comparison of six programs. Tam News 8:4–9

    Google Scholar 

  39. Higginbotham D (1992) Evaluation of keystroke savings across five assistive communication technologies. Augmentative Alternative Commun 8:258–272

    Article  Google Scholar 

  40. Hortsmann HH, Levine SP (1990) Modelling of user performance with computer access and augmentative communication systems for handicapped people. Augmentative Alternative Commun 6:231–241

    Article  Google Scholar 

  41. Hunnicutt S (1987) Input and output alternatives in word prediction. STL/QPRS 2–3/1987, pp 15–29

  42. Hunnicutt S (1989) Using syntactic and semantic information in a word prediction aid. In: Proceedings of the European conference on speech communication and Technology 1, Paris, pp 191–193

  43. Hunnicutt S, Nozadze N, Chikoidze G (2003) Russian word prediction with morphological support. In: 5th International symposium on language, logic and computation, Tbilisi, Georgia

  44. Klund J, Novak M (2001) If word prediction can help, which program do you choose? Retrieved February 16, 2004, from http://www.tracecenter.org/docs/wordprediction2001/

  45. Koester HH, Levine SP (1994) Modelling the speed of text entry with a word prediction interface. IEEE Trans Rehabil Eng 2(3):177–187

    Article  Google Scholar 

  46. Koester HH, Levine SP (1996) Effect of a word prediction feature on user performance. Augmentative Alternative Commun 12:155–168

    Article  Google Scholar 

  47. Koester HH, Levine SP (1998) Model simulations of user performance with word prediction. Augmentative Alternative Commun 14:25–35

    Article  Google Scholar 

  48. Laine CJ (1998) Using word-prediction technology to improve the writing of low-functioning children and adults. In: Proceedings of the Australian computers in education conference. http://www.cegsa.sa.edu.au/Acec98/Papers/P-Laine.html

  49. Laine CJ, Bristow T (1999) Using manual word-prediction technology to cue student’s writing: does it really help? CSUN99. http://www.dinf.org/Csun_99/Session0067.html

  50. Lesher GW, Moulton BJ, Higginbotham DJ (1998) Techniques for augmenting scanning communication. Augmentative Alternative Commun 14:81–101

    Article  Google Scholar 

  51. Lesher GW, Moulton BJ, Higginbotham DJ, Alsofrom B (2002) Limits of human word prediction performance. 2002 technology and persons with disabilities conference, California State University, Northridge

  52. Magnuson S (1995) Word prediction as linguistic support for individuals with reading and writing difficulties. In: Placencia Porrero I, Puig de la Bellacasa R (eds) The European context for assistive technology. IOS Press, Ohmsa, pp 320–323

    Google Scholar 

  53. Magnuson T (1998) Linguistic Evaluation of PROPHET II: a pilot project. In: Proceedings of the Isaac conference, Dublin (Ireland), pp 479–480

  54. National Center to Improve Practice (2004) NCIP Library. http://www2.edc.org/Ncip/Library/Toc.htm

  55. Newell AF, Arnott J, Waller A (1992) On the validity of user modelling. In: AAC: comments on Horstmann and Levine (1990) Augmentative Alternative Commun 8:89–92

  56. Newell AF, Arnott JL, Booth L, Beattie W, Brophy B, Ricketts IW (1992) Effect of the "Pal" word prediction system on the quality and quantity of text generation. Augmentative Alternative Commun 8:304–311

    Google Scholar 

  57. Palazuelos-Cagigas S, Aguilera S, Claypool T, Ricketts I, Gregor P (1998) Comparison of two word prediction systems using five European languages. In: Proceedings of the ISAAC conference, Dublin (Ireland), pp 192–193

  58. Palazuelos-Cagigas S, Aguilera S, Ricketts IW, Gregor P, Claypool T (1998) Artificial neural networks applied to improving linguistic word prediction. In: Proceedings of the ISAAC conference, Dublin (Ireland), pp 194–195

  59. Shannon CE (1951) Prediction and entropy of printed English. Bell Syst Techn J 30(1):50–64

    Google Scholar 

  60. Swiffin AL, Arnott JL, Pickering JA, Newell AF (1987) Adaptive and predictive techniques in a communication prosthesis. Augmentative Alternative Commun 3:181–191

    Article  Google Scholar 

  61. Swiffin AL, Arnott JL, Newell AF (1987) The use of syntax in a predictive communication aid for the physically handicapped. In: RESNA 10th annual conference, San Jose (California), pp 124–126

  62. Tegic Communications (2004) T9 Text Input for Keypad Devices. http://www.tegic.com

  63. Van Dyke JA (1991) Word prediction for disabled users: applying natural language processing to enhance communication. Thesis Submitted For The Degree Of Honors Bachelor of Arts In Cognitive Studies. University of Delaware

  64. Venkatagiri HS (1993) Efficiency of lexical prediction as a communication acceleration technique. Augmentative Alternative Commun 9:161–167

    Article  Google Scholar 

  65. Venkatagiri HS (1999) Efficient keyboard layouts for sequential access in augmentative and alternative communication. Augmentative Alternative Commun 15:126–134

    Article  Google Scholar 

  66. Wester M (2003) User evaluation of a word prediction system. Master’s thesis in computational linguistics, Uppsala University, Uppsala (Finland). http://stp.ling.uu.se/ ∼matsd/thesis/arch/2003_wester.pdf

  67. Wood MEJ, Lewis E (1993) Grammatical recognition in computer aided conversation. In: Proceedings of the European speech communication association workshop on speech and language technology for disabled people. Stockholm (Sweden), pp 115–118

  68. Wood MEJ (1996) Syntactic pre-processing in single-word prediction for disabled people. PhD Thesis of the Department Of Computer Science. University of Bristol

  69. Worthylake K (2000) A platform-independent word prediction editor. Honours Thesis Defence. Acadia University, March. http://cs.acadiau.ca/Seminars/Previous/Kevinworthylake.html

  70. Zordell J (1990) The use of word prediction and spelling correction software with mildly handicapped students Taken From [54]. Closing the Gap 9(1):10–11

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Laboratory of Human-Computer Interaction for Special Needs Informatika Fakultatea, Euskal Herriko Unibertsitatea, Manuel Lardizabal, 1, E-20018, Donostia, Spain

    Nestor Garay-Vitoria & Julio Abascal

Authors
  1. Nestor Garay-Vitoria
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Julio Abascal
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Nestor Garay-Vitoria.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Garay-Vitoria, N., Abascal, J. Text prediction systems: a survey. Univ Access Inf Soc 4, 188–203 (2006). https://doi.org/10.1007/s10209-005-0005-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10209-005-0005-9

Keywords