Improving word prediction for augmentative communication by using idiolects and sociolects
Word prediction, or predictive editing, has a long history as a tool for augmentative and assistive communication. Improvements in the state-of-the-art can still be achieved, for instance by training personalized statistical language models. We developed the word prediction system Soothsayer. The main innovation of Soothsayer is that it not only uses idiolects, the language of one individual person, as training data, but also sociolects, the language of the social circle around that person. We use Twitter for data collection and experimentation. The idiolect models are based on individual Twitter feeds, the sociolect models are based on the tweets of a particular person and the tweets of the people he often communicates with. The sociolect approach achieved the best results. For a number of users, more than 50% of the keystrokes could have been saved if they had used Soothsayer.
Keywords: word prediction, Twitter, idiolect, predictive editing, word completion, language modelling, personalization, augmentative and assistive communication
Published online: 10 November 2014
Aha, D.W., Kibler, D., & Albert, M.K.
Asur, S., & Huberman, B.A.
Bagavandas, M., & Manimannan, G.
(2010) Individual usage: A corpus-based study of idiolects. In Laud conference , Landau, Germany. from http://auckland.academia.edu/MichaelBarlow
Carlberger, A., Carlberger, J., Magnuson, T., Hunnicutt, S., Cagigas, S.E.P., & Navarro, S.A.
(1997) Profet, a new generation of word prediction: An evaluation study. In ACL Workshop on Natural Language Processing for Communication Aids (pp. 23 -28).
(2000) Empirical estimates of adaptation: The chance of two noriegas is closer to p/2 than p2. In Proceedings of the 18th Conference on Computational Linguistics , Vol 1 (pp. 180–186).
(1997) Augmented and alternative nlp techniques for augmented and alternative nlp techniques for augmentative and alternative communication. In Proceedings of the ACL Workshop on Natural Language Processing for Communication Aids (pp. 37–42).
Daelemans, W., Van den Bosch, A., & Weijters, A.
Darragh, J.J., Witten, I.H., & James, M.L.
(1996) An empirical comparison of probability models for dependency grammar. In Technical Report IRCS-96-11, Institute for Research in Cognitive Science. University of Pennsylvania.
Fazly, A., & Hirst, G.
(2003) Testing the eﬃcacy of part-of-speech information in word completion. In Proceedings of the 2003 eacl Workshop on Language Modeling for Text Entry Methods (pp. 9–16).
Garay-Vitoria, N., & Abascal, J.
Garay-Vitoria, N., & Gonzalez-Abascal, J.
(1997) Intelligent word-prediction to enhance text input rate. In Proceedings of the 2nd International Conference on Intelligent User Interfaces (pp. 241–244).
Heil, B., & Piskorski, M.
(2009) New twitter research: Men follow men and nobody tweets( Blog No. June 1). http://blogs.hbr.org/cs/2009/06/new\twitter\research\men\follo.html.
Horstmann Koester, H., & Levine, S.P.
How, Y., & Kan, M.-Y.
Langlais, P., Foster, G., & Lapalme, G.
(2000) Transtype: A computer-aided translation typing system. In Proceedings of the 2000 NAACL-ANLP Workshop on Embedded Machine Translation Systems , Vol 5 (pp. 46–51).
Lesher, G.W., Moulton, B.J., & Higginbotham, D.J.
(1999) Eﬀects of Ngram order and training text size on word prediction. In Proceedings of the Annual Conference of the Resna (pp. 52–55).
Matiasek, J., Baroni, M., & Trost, H.
Nantais, T., Shein, F., & Johansson, M.
(2001) Eﬃcacy of the word prediction algorithm in wordq. In Proceedings of the 24th Annual Conference on Technology and Disability , RESNA.
Oostdijk, N., Reynaert, M., Hoste, V., & Schuurman, I.
Rui, H., & Whinston, A.
Shein, F., Nantais, T., Nishiyama, R., Tam, C., & Marshall, P.
(2001) Word cueing for persons with writing diﬃculties: Wordq. In Proceedings of csun 16th Annual Conference on Technology for Persons with Disabilities .
Stocky, T., Faaborg, A., & Lieberman, H.
Swiﬃn, A.L., Pickering, J.A., Arnott, J.L., & Newell, A.F.
(1985) PAL: An eﬀort eﬃcient portable communication aid and keyboard emulator. In Proceedings of the 8th Annual Conference on Rehabilitation Technology , resna (pp. 197–199).
Van den Bosch, A.
Van den Bosch, A., & Bogers, T.
(2008) Eﬃcient context-sensitive word completion for mobile devices. In Mobilehci 2008: Proceedings of the 10th International Conference on Human-Computer Interaction with Mobile Devices and Services, IOP-MMI Special Track (pp. 465–470).
Verberne, S., Van den Bosch, A., Strik, H., & Boves, L.
(2012) The eﬀect of domain and text type on text prediction quality. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics , Avignon, France (pp. 561–569). New Brunswick, NJ: ACL.
Cited by 1 other publications
Cucchiarini, Catia & Monique Lamers
This list is based on CrossRef data as of 11 may 2021. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.