Salman Ahmad FayyazMuhammad SheheryarAli Zafar2018-01-122018-01-122016https://escholar.umt.edu.pk/handle/123456789/2439Supervised by: Dr Mazhar JavedIn this project, we propose an automatic generation system of multiple-choice cloze questions from English texts. Experimental knowledge is necessary to produce appropriate questions, so machine learning is introduced to acquire knowledge from existing questions. To generate the questions from texts automatically, the system extracts appropriate sentences for questions from texts based on Preference Learning, estimates a blank part based on Conditional Random Field, and Generates Distracters based on statistical patterns of existing questions. Experimental results show our method is workable for selecting appropriate sentences and blank part. Moreover, our method is appropriate to generate the available distractersenPreference LearningConditional Random FieldBSCS THESISThesis