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.

多项选择题 (MCQ) 被用作评估的工具工具，不仅在各种竞争性考试中，而且在当代基于信息和通信技术 (ICT) 的教育、主动学习等中。 因此，多项选择题的自动生成来自基于文本的学习材料的项目在计算机辅助评估中是一项真正艰巨的任务。过去二十年来为此目的开发了许多系统，但系统生成的问题未能满足基于计算机的自动化评估的需求。因此，这仍然是教育技术和自然语言处理研究的开放领域。本文介绍了一种用于生成带有干扰项的多项选择测试项目的自动化系统。系统首先使用主题词或关键词（一个或多个词）选择信息性句子。选择句子中的最佳关键字作为答案关键字。接下来，系统从这个句子中删除答案关键字并将其转换为问题句子（词干）。错误的选项或干扰项是使用基于特征的聚类方法自动生成的，无需使用任何外部信息或知识库。结果突出了所提出的用于生成带有干扰项的 MCQ 的系统的效率。不使用任何外部信息或知识库。结果突出了所提出的用于生成带有干扰项的 MCQ 的系统的效率。不使用任何外部信息或知识库。结果突出了所提出的用于生成带有干扰项的 MCQ 的系统的效率。