No description available.

People with some types of motor disabilities who wish to generate text using a computer can find the process both fatiguing and time-consuming. These problems can be alleviated by reducing the quantity of keystrokes they must make, and one approach is to allow the user to enter shortened, abbreviated input, which is then re-expanded for them, by a program ‘filling in the gaps’. Word Prediction is one approach, but comes with drawbacks, one of which is the requirement that generally the user must type the first letters of their intended word, regardless of how unrepresentative they may consider those letters to be. Abbreviation Expansion allows the user to type reduced forms of many words in a way they feel represents them more effectively. This can be done by the omission of one or more letters, or the replacement of letter sequences with other, usually shorter, sequences. For instance, the word ‘hyphenate might be shortened to ‘yfn8’, by leaving out some letters and replacing the ‘ph’ and ‘ate’ with the shorter but phonetically similar ‘f’ and ‘8’. ‘Fixed Abbreviation Expansion’ requires the user to memorise a set of correspondences between abbreviations and the full words which they represent. While this enables useful keystroke savings to be made, these come alongside an increased cognitive load and potential for error. Where a word is encountered for which there is no preset abbreviation, or for which the user cannot remember one, keystroke savings may be lost. ‘Flexible Abbreviation Expansion’ allows the user to leave out whichever letters they feel to be ‘less differentiating' and jump straight ahead to type those they feel are most ‘salient’ and most characterise the word, choosing abbreviations ‘on the fly’. The need to memorise sets of correspondences is removed, as the user can be offered all candidates for which the abbreviation might be a representation, usually in small sets on screen. For useful savings to be made, the intended word must regularly be in the first or second set for quick selection, or the system might attempt to place the intended word at the very top of its list as frequently as possible. Thus it is important to generate and rank the candidates effectively, so that high probability words can be offered in a shortlist. Lower-ranking candidates can be offered in secondary lists which are not immediately displayed. This can reduce both the cognitive load and keystrokes needed for selection. The thesis addresses the task of reducing the number of keystrokes needed for text creation with a large, expressive vocabulary, using a new approach to flexible abbreviation expansion. To inform the solution, two empirical studies were run to gather letter-level statistics on the abbreviation methods of twenty-nine people, under different degrees of constriction (that is, different restrictions on the numbers of characters by which to reduce). These studies showed that with a small amount of priming, people would abbreviate in regular ways, both shared between users, and repeated through the data from an individual. Analysis showed the most common strategies to be vowel deletion, phonetic replacement, loss of double letters, and word truncation. Participants reduced the number of letters in their texts by between 25% (judged to maintain a high degree of comprehensibility) up to 40% (judged to be a maximum degree of brevity whilst still retaining comprehensibility). Informed by these results, an individual-word-level algorithm was developed. For each input abbreviation, a set of candidates is produced, ranked in such a way as to potentially save substantial keystrokes when used across a whole text. A variety of statistical and linguistic techniques, often also used in spelling checking and correction, are used to rank them so that the most probable will be easiest to select, and with fewest keystrokes. The algorithm works at the level of the individual word, without looking at surrounding context. Evaluation of the algorithm demonstrated that it outperforms its nearest comparable alternative, of ranking word lists exclusively by word frequency. The evaluation was performed on the data from the second empirical study, using vocabulary sizes of 2-, 10-, 20- and 30-thousand words. The results show the algorithm to be of potential benefit for use as a component of a flexible abbreviation expansion system. Even with the overhead of selection of the intended word, useful keystroke savings could still be attained. It is envisaged that such a system could be implemented on many platforms, including as part of an AAC (Augmentative and Alternative Communication) device, and an email system on a standard PC, thus making typed communication for the user group more comfortable and expansive.

No description available.

Assistive technology, specifically, word prediction software holds great promise in supporting the writing process for students with learning disabilities. This thesis reports on a qualitative study that examined eight students’ self-perceptions as learners and writers using word prediction software. Participants were purposefully recruited from a local Learning Disabilities Association’s listserv located in a mid-sized Eastern Ontario city. Three groups of two to three Grades 4-8 students previously identified with a learning disability, and who were already using word prediction software (e.g. Co-Writer or WordQ), attended a 3-hour session. This session included an instructional workshop, and completion of a short reflective writing task followed by a focus group. Separately, participants’ parents attended a focus group. Data for this study includes focus group responses (student and parent), observations from the workshop, and the written student reflections. Using content analysis, emerging themes from participant responses were analyzed. The main themes from this analysis were: (1) students’ perceptions of having an equal opportunity to participate in academic subjects; (2) increased student self-efficacy; and (3) an ad hoc approach to training and the use of assistive technology software in school. These themes were then linked to relevant literature and a set of recommendations was developed for educators. Recommendations for the future included facilitating increased self-efficacy for students with learning disabilities; reducing the ad hoc approach to teacher education by instituting mandatory courses about students with disabilities in teacher education programs; and increased instruction in the use of assistive technology for parents and teachers. / Thesis (Master, Education) -- Queen's University, 2011-06-27 22:45:11.704

Writing is a multifaceted, complex task that involves interaction between physical and cognitive skills. Individuals with physical disabilities vary in terms of both their physical and cognitive abilities. Often they must overcome one or more significant barriers in order to engage in the task of writing. Minimizing or eliminating barriers is important because opportunities are greater for individuals who can effectively communicate their ideas via writing. Assistive technology (AT) is an increasingly effective solution to increase typing fluency. The purpose of this study is to examine if word prediction software, a commonly used software program used with individuals with learning disabilities, will be effective for those with physical impairments to increase typing rate and reduce spelling errors (fluency). Data will be collected for words correct per minute (WCPM) and errors (e.g., spelling). Four middle- or high school-aged participants with diverse physical disabilities will be recruited in this single subject, alternating treatment design. Participants will type for three-minute timed sessions using either a standard word processor or Co:Writer 4000, a word prediction software program. Specific research questions are: (a) to what extent will students with physical and health disabilities produce greater WCPM when writing a draft paper on a common topic using word prediction rather than word processing, (b) to what extent will the use of word prediction software result in the production of different types of errors compared to errors produced using word processing, (c) to what extent will the use of word prediction software increase accuracy by decreasing spelling errors, (d) to what extent will more text be produced using word prediction software than with word processing, and (e) to what extent will word prediction increase motivation or willingness to write? Data will be graphed and analyzed for bifurcation. Bifurcation will be determined by examination of the means, level of performance, and trend. Finally, examination of errors will be used to verify spelling accuracy.

Abstract The problem addressed in the present thesis is the utility of linguistic knowledge in one domain of language technology, word prediction. An important characteristic of any practical language technology application is its level of performance, and it is therefore essential to be able to measure this quantitatively. The main questions in the present thesis are the following: (1) how can a significant improvement in performance be obtained in practical language technology products, and (2) what is the cost of improved performance in terms of the sources of linguistic knowledge that should be incorporated in them? On a more general level, the major findings suggest that the practical utility of linguistic knowledge in language technology should generally be evaluated from at least three larger perspectives: (1) language, (2) technology, and (3) the user of the application. From these three perspectives, a variety of constraints can be identified which either increase or decrease the usefulness of linguistic knowledge in practical language technology applications. A statistical state-of-the-art word prediction system was developed and tested in the empirical part of this work, and testing the performance of a few prediction methods that utilise sources of linguistic knowledge showed that they can perform just as well as some existing state-of-the-art statistical prediction methods. When the syllable-initial characters of the words to be predicted were used, for example, the expected length of the search key in a running text with a prediction list of ten tokens was only 1.59 characters, while the use of information on the parts of speech of the word tokens to be predicted in a system with five lists representing five parts of speech resulted only in a three percent improvement in performance. One of the practical implications of these results for the field of language technology is that a significant improvement in the performance of a word prediction system may be achieved only incrementally. The simultaneous use of several techniques may in turn dilute the real-time operation of the prediction system, so that it is unable to suggest candidate words quickly enough for the user. It can also affect some performance aspects such as the average percentage of keystrokes/characters saved. / Abstrakti Tässä työssä tutkittiin lingvistisen tiedon hyödyllisyyttä kieliteknologian yhdellä sovellusalueella eli sanan ennakointia englannin kielessä. Sovellus pyrkii ennakoimaan sanan, jota käyttäjä kirjoittaa parhaillaan tai aikoo kirjoittaa seuraavaksi. Nämä sovellukset ovat hyödyllisiä esim. pienissä päätelaitteissa, joissa tekstin tuottaminen on hankalaa. Eräs kieliteknologiasovellusten tärkeimmistä ominaisuuksista on niiden tehokas toiminta ja suorituskyky, jonka tulisi olla kvantitatiivisesti mitattavissa. Oleellisin tutkimuskysymys on näin ollen: (1) miten käytännön kieliteknologiasovellusten suorituskykyä voidaan parantaa merkittävästi lingvistisen tiedon avulla ja (2) mitä tämä vaatii käytännössä? Yleisellä tasolla tutkimuksen tärkeimmät tulokset ovat seuraavat: lingvistisen tiedon käytännön hyödyllisyyttä pitäisi arvioida ainakin kolmesta näkökulmasta, jotka ovat: (1) kielen näkökulma, (2) teknologian näkökulma ja (3) sovelluksen käyttäjän näkökulma. Näiden kolmen näkökulman avulla voidaan määrittää joukko tekijöitä, jotka joko lisäävät tai vähentävät lingvistisen tiedon hyödyllisyyttä käytännön kieliteknologiasovelluksissa. Työn empiirisessä osassa kehitettiin tilastollinen sananennakointisovellus englannin kieleen hyödyntäen parhaiten toimivia ennakointitekniikoita yhdessä ja samassa järjestelmässä. Kehitetyssä järjestelmässä suorituskyky vastaa täysin aiempien järjestelmien suorituskykyä. Työssä testattiin myös joitakin uusia, lingvististä tietoa hyödyntäviä ennakointitekniikoita, joiden suorituskyky vastasi tiettyjen tilastollisten ennakointimenetelmien suorituskykyä. Tutkimuksen tuloksista voidaan päätellä muun muassa, että sananennakointisovellusten suorituskykyä voidaan parantaa merkittävästi lingvistisen tiedon avulla vain käyttämällä samanaikaisesti useita lingvistisen tiedon lähteitä. Tämä taas saattaa hidastaa sovelluksen reaaliaikaista toimintaa ja vaikuttaa sovelluksen suorituskykyyn silloin kun se mitataan näppäinsäästönä merkkisäästön asemesta.

Personer med kognitiva funktionsnedsättningar kan ha olika svårigheter med att skriva på mobila enheter som mobiltelefoner och surfplattor. Svårigheterna kan vara att stava korrekt och skriva i normal skrivhastighet. Denna studie vill jämföra olika skrivhjälpmedel mot utan skrivhjälpmedel för att utvärdera vilka som kan bidrar till bättre skrivhastighet och färre stavfel. Studien vill också utvärdera vad personer med kongitiva funktionsnedsättningar tycker om dessa skrivhjälpmedel för att i framtiden kunna utveckla bättre programvara. Skrivhjälpmedlen som användes i studien är; ● Ordprediktion ● Ordprediktion med ett lättläst lexikon ● Tangentbordsprediktion ● Ordprediktion med tangentbordsprediktion Studien har två frågor som besvarades. Den första frågan handlade om hur personer med kognitiva funktionsnedsättningar tyckte om de olika skrivhjälpmedlen. Den andra handlade om hur skrivhjälpmedlen påverkade testdeltagarnas skrivhastighet, knapptryckningsbesparingar samt skrivfel. För att besvara dessa frågor användes withinsubject design. Data som samlades in var kvantitativ, där första frågan samlade in data via enkäter medan den andra samlade in via tester som var tillgängliga via en applikation. Resultaten visade på att alla ordprediktionsmetoder ökade skrivhastigheten, minskade knapptryckningar och minskade skrivfelen i någon grad. Ordprediktion med lättläst höjde skrivhastigheten mest till 9,87 ord i minuten jämfört med utan prediktion som hade 7,67 ord i minuten. Flest knapptryckningsbesparingar hade ordprediktion, med en besparingsmängd på 14,04%. Det var väldigt få skrivfel för alla prediktionsmetoder, men de hade alla bättre resultat än utan prediktion som hade flest skrivfel per person. Deltagarna tyckte för det mesta om alla skrivhjälpmedel och kunde tänka sig använd dem i framtiden. Resultaten för alla testerna kunde inte alltid påvisas med statistisk signifikans. Denna uppsats kan hjälpa utvecklare av skrivhjälpmedel för personer med kognitiva funktionsnedsättningar att bestämma vilken typ av skrivhjälpmedel de kan satsa på för utveckling. / People with cognitive disabilities can have various difficulties with typing on mobile devices(smartphones or tablets). The difficulties they face could be spelling and writing in normal typing speed. This study has compared different writing aids against no writing aid in the means to evaluate which ones can help improve typing speed and spelling. The study has also evaluated what people with cognitive disabilities think about these type of writing aids to help future development of software. The writing aids used in the study were; ● Word prediction ● Word prediction with a easy dictionary ● Keyboardprediction ● Word prediction combined with keyboardprediction The study answered two questions. The first question was what people with cognitive disabilities thought about the writing aids used in the study. The second answered whether the writing aids improved test participants writing speed, keystroke savings and spelling. To answer these questions a withinsubject design was used. The data collected was quantitative, where the first question collected data through questionnaires while the other collected via tests that were available via an application. The goal of this study was to test four different writing aids and compare them against writing without aid to show which can contribute most to the increase in write speed, to the reduction of keystrokes and reduction in typos. To reach these targets we used a withinsubject design, meaning that all participants tested all writing aids. Participants were given a few short questions on the writing aids after the tests through surveys. Collection of data was through a quantitative approach. The results showed that all writing aids increased writing speed, decreased keystrokes and improved spelling. Word prediction with an easy dictionary increased writing speed the most, to 9,87 words per minute, compared to results without prediction which had 7.67 words per minute. Word prediction had the most keystroke savings, with a savings amount of 14,04%. There were very few typing errors for all prediction methods, but they all had better results than without prediction which had the most errors per person. However, only some of these results could be shown with statistical significance. This paper can help developers who develop write aids for people with cognitive disabilities to determine what type of writing aid they may invest in development.

Word prediction has been offered as support for children with spelling difficulties. The literature however has shown wide-ranging results, as the use of word prediction is at the cost of time and fatigue due to increased visual-cognitive demands. Spelling support with word prediction is through word completion, keystroke reduction and the interactive process between spelling and reading. The research project was a cross-over within-subject design using 80 Grade 4 – 6 children with spelling difficulties in a school for special needs. The research task took the form of entering 30 words through an on-screen keyboard, with and without the use of word prediction software. The subjects were divided into four groups, who completed the research task in combinations of one of two equivalent wordlists and the presentation order of the typing method used. The Graded Word Spelling Test, administered before the study began, served to investigate whether there was a relationship between the children’s current spelling knowledge and word prediction efficacy. The results indicated an increase in spelling accuracy with the use of word prediction, but at the cost of time and the tendency to use word approximations, which decreased as grade and age increased. Children’s current spelling knowledge could not serve as an indicator of who would be most likely to benefit from word prediction use. The cross-over design counter-balanced the effects of the inequalities in the two wordlists and the effects of practice and fatigue noted in the presentation order. Further research into the impact that more extensive training and practice would have on word prediction efficacy and the usefulness of word prediction in more functional writing is necessary. / Dissertation (M (Augmentative and Alternative Communication))--University of Pretoria, 2005. / Centre for Augmentative and Alternative Communication (CAAC) / unrestricted

Ce travail de thèse avait pour objectif principal d’étudier l’influence de certains paramétrages deslogiciels de prédiction de mots et d’un programme d’entraînement ciblé sur la vitesse de saisie detexte chez des personnes tétraplégiques. Six études ont été menées. L’étude 1 nous a permis demettre en évidence des vitesses de saisie de texte chez les personnes tétraplégiques et d’étudierl’influence de leurs aides techniques d’accès à l’outil informatique sur cette vitesse. L’étude 2 nous apermis de mettre en avant l’hétérogénéité des résultats d’un logiciel de prédiction de mots sur lavitesse de saisie de texte sur une population hétérogène et sans paramétrage de ces logiciels.L’étude 3 nous a permis d’étudier les habitudes de préconisations et de paramétrages des logiciels deprédictions de mots par les professionnels. Les études 4 et 5 nous ont permis d’évaluer l’influencedes paramétrages (nombre de mots affichés dans la liste de prédiction et l’adaptation du logiciel auvocabulaire de l’utilisateur) sur cette saisie de texte. Enfin, l’étude 6 nous a permis d’étudierl’influence d’un entraînement dirigé par des professionnels sur les logiciels de prédictions de motschez des personnes tétraplégiques, sur la vitesse de saisie de texte.Les résultats montrent que seule l’aide technique d’accès à l’outil informatique influence la vitessede saisie de texte. Les logiciels de reconnaissance vocale permettent une vitesse de saisie de texteéquivalente à celle des personnes valides utilisant un clavier standard. Les paramétrages (nombre demots affichés dans la liste de prédiction et l’adaptation du logiciel au vocabulaire de l’utilisateur) ontune influence différente en fonction du niveau lésionnel des personnes tétraplégiques sur la vitessede saisie de texte, le nombre d’erreurs ou le confort. De plus, une différence entre l’importancedonnée aux paramétrages par les professionnels préconisateurs et les paramétrages effectivementréglés a été mise en évidence. Enfin, l’influence d’un entraînement dirigé sur la vitesse de saisie detexte a été mise en évidence sur la vitesse de saisie de texte. Au regard de l’ensemble de cesrésultats, il apparait nécessaire de paramétrer les logiciels de prédictions de mots, mais aussi deconnaitre l’influence des différents réglages et de diffuser cette information au sein des réseauxprofessionnels. La recherche doit être poursuivie pour améliorer les logiciels de prédiction de mots,mais aussi pour favoriser de nouveaux outils tels les tablettes tactiles et les logiciels dereconnaissance vocale. Une systématisation des entraînements dirigés sur les logiciels de prédictionde mots nécessite une réflexion et une validation sur les modalités et la nature de cesaccompagnements. / The main objective of this work was to study the influence of key settings of word predictionsoftware as well as a training program on the use of word prediction, on text input speed in personswith cervical spinal cord injury.Study 1 determined text input speed in persons with cervical spinal cord injury and the influence ofpersonal characteristics and type of computer device on text input speed. Study 2 evaluated theeffect of a dynamic virtual keyboard coupled with word prediction software on text input speed inpersons with functional tetraplegia. Study 3 analysed the word prediction software settingscommonly prescribed by health-related professionals for people with cervical spinal cord injury.Studies 4 and 5 evaluated the influence of the number of words displayed in the prediction list andthe frequency of use setting on text input speed. Finally, study 6 evaluated the influence of a trainingprogram on the use of word prediction software for persons with cervical spinal cord injury on textinput speed.The results showed that only the type of computer device influenced text input speed; voicerecognition software increased the text input speed of persons with cervical spinal cord injury to thatof able-bodied people using a standard keyboard. The influence of the different word predictionsoftware settings (number of words displayed in the prediction list and the frequency of use) on textinput speed, the number of errors or comfort of use, differed depending on the level of injury. Wealso found differences between the perception of the importance of some settings by healthprofessionalsand data in the literature regarding the optimization of settings. Moreover, althoughsome parameters were considered as very important, they were rarely configured. Finally, trainingpersons with cervical spinal cord injury in the use of word prediction software increased text inputspeed.The results of this work highlighted that word prediction software settings influence text input speedin persons with cervical spinal cord injury, however not all professionals are aware of this.Information should therefore be disseminated through professional networks. Further studies shouldaim to improve word prediction software and should also focus on new devices such as tablets andvoice recognition software. Persons with cervical spinal cord injury training programs in the use ofword prediction software need to be developed and validated.