You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This project develops an effective spell correction system for Roman Urdu using the Noisy Channel model. 4 components: language model, error model, candidate generation, and selection model. Suggests the most likely correction for a given incorrect word using probabilistic approach.
We have presented a new dataset for question and answering models. Our dataset contains 27 different Urdu paragraphs which are taken from different available resources i.e Urdu Wikipedia, youtube and news articles etc. All selected paragraphs have an average of 3 to 7 questions along with their possible answers that range from 1 to 3. The data c…