The Language Component of the Fasty Text Prediction System

Trost, Harald; Matiasek, Johannes; Baroni, Marco

doi:10.1080/08839510500191901

Cited by 16 publications

(20 citation statements)

References 15 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous works already emphasized the importance of adaptation for AAC systems [cf., Trost et al 2005;Trnka et al 2006;. Whereas these works only consider user adaptation, we have now investigated two kinds of adaptation:…”

Section: The Base Model Of Sibywordmentioning

confidence: 98%

“…On the one hand, there are methods like the ones described in Trost et al [2005] and Li and Hirst [2005] that make use of the trigger model, as presented by Rosenfeld [1996].…”

Section: Semantic Adaptation: Related Workmentioning

confidence: 99%

“…Boissière and Dours [2001]), an approach often referred to as 'word completion'. On the other hand, a list of words is provided [Trost et al 2005;Berard and Neimeijer 2004], from which the user can then select the intended word.…”

Section: Interface Design Of An Aac Systemmentioning

confidence: 99%

“…In particular, they are not able to use the standard input devices of a computer. Like other AAC systems, such as FASTY [Trost et al 2005] or Dasher [Ward et al 2000] SIBYLLE aims at restoring the communicative abilities of these persons.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sibylle, An Assistive Communication System Adapting to the Context and Its User

Wandmacher

Antoine

Poirier

et al. 2008

ACM Trans. Access. Comput.

View full text Add to dashboard Cite

In this article, we describe the latest version of Sibylle, an AAC system that permits persons who have severe physical disabilities to enter text with any computer application, as well as to compose messages to be read out through speech synthesis. The system consists of a virtual keyboard comprising a set of keypads that allow for the entering of characters or full words by a single-switch selection process. It also includes a sophisticated word prediction component which dynamically calculates the most appropriate words for a given context. This component is auto-adaptive, that is, it learns with every text the user enters. It thus adapts its predictions to the user's language and the current topic of communication as well. So far, the system works for French, German and English. Earlier versions of Sibylle have been used since 2001 in a rehabilitation center (Kerpape, France).

show abstract

Section: The Base Model Of Sibywordmentioning

confidence: 98%

“…On the one hand, there are methods like the ones described in Trost et al [2005] and Li and Hirst [2005] that make use of the trigger model, as presented by Rosenfeld [1996].…”

Section: Semantic Adaptation: Related Workmentioning

confidence: 99%

Section: Interface Design Of An Aac Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sibylle, An Assistive Communication System Adapting to the Context and Its User

Wandmacher

Antoine

Poirier

et al. 2008

ACM Trans. Access. Comput.

View full text Add to dashboard Cite

show abstract

“…Most of them only attempt to predict the next single word [50] and/or they are concerned about measuring the accuracy of off-line text predictions [2]. Here, we consider a more general setting where not only single words but multi-word fragments or full sentences are predicted under an interactive paradigm.…”

Section: Introductionmentioning

confidence: 99%

Interactive Pattern Recognition applied to Natural Language Processing

Ruiz¹

View full text Add to dashboard Cite

ACKNOWLEDGMENTSQuiero aprovechar estas líneas para mostrar mi agradecimiento a todas las personas que de una forma o de otra han contribuido a que esta tesis se haya hecho realidad.En primer lugar quiero agradecer sinceramente a mis directores de tesis todo su apoyo, paciencia y dedicación. Ismael, a quién hace tiempo que no considero simplemente mi director de tesis, sino un amigo y del que he aprendido muchas cosas, sobre todo en cuanto a traducción automática se refiere. En cuanto a Enrique, no puedo sino considerarlo como un auténtico maestro para mí. Gracias por enseñarme que el detalle es realmente importante y por reconducir mis raras e improvisadas propuestas. En definitiva, si de alguna forma ahora puedo considerarme un investigador, es fundamentalmente gracias a ellos. También me gustaría incluir aquí a Francisco Casacuberta, con quien he compartido varios proyectos y artículos y del que también he tenido oportunidad de aprender muchas cosas.No quiero dejar pasar la oportunidad de agradecer a todos los que de uno u otro modo han compartido conmigo su aprendizaje en el mundo de la investigación. Empezando con mis compañeros en el proyecto TT2: Antonio, Elsa y Jorge, con quien tantos momentos entrañables compartí. Extiendo este agradecimiento a todos los miembros del ITI que me brindaron una extraordinaria acogida durante mis casi tres años en Valencia: Alejandro (quien siempre tiene algún truco nuevo que enseñarte), José Ramón, Dani (con quien siempre se mantienen conversaciones productivas), Javi, Jose, Jorge, Vicent y a todos los miembros del grupo PRHLT. También quiero agradecer a todos los integrantes del grupo SIMD, especialmente a sus directores José Antonio y José Miguel por acogerme a mi regreso de Valencia. Porúltimo, quiero también mostrar mi agradecimiento a José Oncina, por encontrar un algoritmo que hace mejores los resultados de predicción de texto aquí presentados.En el aspecto personal, quiero agradecer a mis padres todo su apoyo y cariño en las diferentes etapas de mi vida. También al resto de mi familia. A todos mis amigos, por saber perdonar mi falta de dedicación con ellos debido a lo absorbente de este trabajo. Porúltimo, mi más profundo agradecimiento a Sonia, por todo su apoyo y amor durante estos años tan complicados.Finalmente, y citando a los geniales "Monty Python": and now, for something completely different ... Luis Rodríguez Ruiz ABSTRACTThis thesis is about Pattern Recognition. In the last decades, huge efforts have been made to develop automatic systems able to rival human capabilities in this field. Although these systems achieve high productivity rates, they are not precise enough in most situations. Humans, on the contrary, are very accurate but comparatively quite slower. This poses an interesting question: the possibility of benefiting from both worlds by constructing cooperative systems.This thesis presents diverse contributions to this kind of collaborative approach. The point is to improve the Pattern Recognition systems by properly introducing a human operator i...

show abstract