Multiple-choice question generation with auto-generated distractors for computer-assisted educational assessment

Abstract

Multiple-choice questions (MCQs) are used as instrumental tool for assessment, not only in various competitive examinations but also in contemporary information and communications Technology (ICT)-based education, active learning, etc. Therefore, automatic generation of multiple-choice test items from text-based learning material is a truly demanding task in computer aided-assessment. A lot of systems were developed in the past two decades for this purpose, but the system generated questions have failed to satisfy the needs of computer-based automated assessment. As a consequence, this is still an open area of research in education technology and natural language processing. This article presents an automated system for generating multiple-choice test items with distractors. The system first selects informative sentences using the topic-words or keywords (one or more words). The best keyword from a selected sentence is chosen as an answer key. Next, the system eliminates the answer key from this sentence and transforms it into a question-sentence (stem). The wrong options or distractors are generated automatically using a feature-based clustering approach, without using any external information or knowledge-base. The result highlights the efficiency of the proposed system for generating MCQs with distractors.

Aspect based sentiment analysis using multi‐criteria decision‐making and deep learning under COVID‐19 pandemic in India

“…The PMI is chosen as best criterion because it measures the association between a pair of words or phrases and aggregates all the possible weights [ 44 ]. The TF‐IDF is the worst criterion because it is only based on the word frequency and it is not useful for extracting multiword aspect terms [ 45 ]. After finding the lowest and maximum optimum weights for every criterion, we calculate the centre of the interval which is treated as the optimum weight to extract the high level information.…”

Closing the Gap: Automated Distractor Generation in Japanese Language Testing

“…These methods have since evolved into more modern versions, which tend to use semantically related words acquired through WordNet [66,67], a thesaurus [22], or n-grams and collocations [23,68]. Recently, word embeddings have been shown to be effective distractors, and the Word2vec method has gained popularity as a generation method [4,25,47], which achieves semantically similar words. Automatic distractors' generation in languages other than English has also gained more attention in the last decade with improvements to NLP methods, allowing for training models in multiple languages [48].…”

“…To this end, researchers have proposed automatic distractor generation for many of the major languages of the world, e.g., Chinese Mandarin [11], Hindi [24,25], French [12], and English [3,19]. However, to our knowledge, Japanese lacks these types of studies.…”

“…We use NLP to get the difficulty of a cloze test for the automatic evaluation. For the manual evaluation, we asked professional Japanese teachers to evaluate the automatic cloze test questions through a questionnaire, similar to other works in this field [10,25,26].…”

Development of system for generating questions, answers, distractors using transformers

“…Schools and universities usually conduct tests where students are required to pick the right answer from several options or fill missing words. To assess knowledge, multiple-choice questions (MCQ), true/false (T/F) and fill-in-the-blank (FiB) are widely used tools [7].…”