Automatic Generation of Context-Based Fill-in-the-Blank Exercises Using Co-occurrence Likelihoods and Google n-grams

In this paper, we propose a method of automatically generating multiple-choice fill-inthe-blank exercises from existing text passages that challenge a reader’s comprehension skills and contextual awareness. We use a unique application of word co-occurrence likelihoods and the Google n-grams corpus to select words with strong contextual links to their surrounding text, and to generate distractors that make sense only in an isolated narrow context and not in the full context of the passage. Results show that our method is successful at generating questions with distractors that are semantically consistent in a narrow context but inconsistent given the full text, with larger n-grams yielding significantly better results.