Next Word Predictor

Typing is probably one of the most frequent activties 90% of the people do 90% of the day. Either through cellphones, tablets or personal computers. However, the way we implement this activity is far from being effective.

OBSERVATIONS

• Typing takes a VERY LONG time.
• Very frequently we use the same phrases or sentences.

In this presentation I will introduce the "Next Word Predictor” app that allows to infer based on previous written words which word is most likely to proceed.

The underlying algorithm of the “Next Word Predictor” is as follows:

• Step 1: Obtain n gram statistics on a large text sample (i.e. 1,2,3,…,n)
• Step 2: Given a sentence with m words, to predict m+1 I check if the previous n-1 words match any of the first n-1 words of any n gram I have. If there is at least a match, select the corresponding matching n gram with the highest frequency, provide the nth word of the n gram as a prediction and stop. Otherwise, move to Step 3.
• Step 3: Apply Step 2 recursively by decresing n until n = 1. If no prediction can be presented an empty string is provided.

• Typing is a deep part of our lives as it is walking and eating.
• The less time we spend on writing something, the more time we will have to enjoy other things.
• The “Next Word Predictor” is an app that allows you to know what word you will probably write in a sentence even before you thought of it!! :)