Predictive virtual keyboard

A non-transitory computer-readable storage device comprising instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

• receiving an indication of at least two contacts at a region of a presence-sensitive screen that outputs virtual keyboard, the at least two contacts constituting a sequence of contacts and being associated with a predicted word and a probability for the predicted word;
• receiving an indication of a third contact at the region of the presence-sensitive screen;
• applying a probabilistic model based on a spatial location of the third contact and the predicted word, wherein the spatial location is based on a distance of the third contact from a location within the virtual spacebar key, the probabilistic model configured to interpret the third contact as at least (i) a selection of the predicted word, wherein the predicted word has a same number of characters as a number of contacts in the sequence of contacts, (ii) a selection of the predicted word, wherein the predicted word has a greater number of characters than the number of contacts in the sequence of contacts, and (iii) a user input of a non-space character;
• and
• updating an input buffer based on an interpretation of the third contact, the interpretation being based on the probabilistic model.

A computing device comprising:

• one or more processors;
• and
• at least one module operable by the one or more processors to:
• receive an indication of at least two contacts at a region of a presence-sensitive screen that outputs a virtual keyboard, the at least two contacts constituting a sequence of contacts and being associated with a predicted word and a probability for the predicted word;
• receive an indication of a third contact at the region of the presence-sensitive screen;
• apply a probabilistic model based on a spatial location of the third contact and the predicted word, wherein the spatial location is based on a distance of the third contact from a location within the virtual spacebar key, the probabilistic model configured to interpret the third contact as at least one of (i) a selection of the predicted word, wherein the predicted word has a same number of characters as a number of contacts in the sequence of contacts, (ii) a selection of the predicted word, wherein the predicted word has a greater number of characters than the number of contacts in the sequence of contacts, and (iii) a user input of a non-space character;
• and
• update an input buffer based on an interpretation of the third contact, the interpretation being based on the probabilistic model.