Text2Picto and Picto2Text are two complementary translation tools aimed at enhancing communication for people with reading disabilities.
Text2Picto translates sentences into pictographs – that is, graphic symbols that serve as stand-ins for verbal communication – while Picto2Text does the reverse by allowing users to select the pictographs that they want to translate into written text. Both tools have been developed by the Centre for Computational Linguistics at the University of Leuven.
Additonal features were added to the tools. Demos of these features are available for Dutch:
- Spelling Correction, which is a crucially important feature since the users of Text2Picto often spell phonetically.
- Word-Sense Disambiguation, which identifies the correct sense of polysemous words and retrieves the correct pictograph for that sense.
- Text2Picto + Simplification & Temporal Detection, which adds pictographs depicting temporal relations between the other symbols and simplifies syntactic structure.
This demo illustrates a number of metrics that quantify the syntactic differences between two sentences. These sentences can (but need not) be written in a different language. Such metrics are for instance useful when comparing a (machine) translation with the original source text, to find differences and similarities between two different translations, or to see how a machine translation differs from a reference translation.
MATEO: Machine Translation Evaluation Online
A first demo to show the basic principles of machine translation evaluation, and how online interfaces can facilitate the process. This is a very early version.