Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Literature Review
Results
Conclusion & Future Scope
References

IRJET- Automated MCQ Generator using Natural Language Processing

Profile image of IRJET JournalIRJET Journal

2021, IRJET

Abstract

Examinations and Assessments are undergoing a tremendous revolution. Universities, colleges, and other educational institutes are increasingly shifting towards online examinations. The pattern of assessment is majorly shifting towards the objective assessment i.e. MCQ based, it is very hard to construct and requires a considerable amount of time for setting numerous questions. There's a growing need for a costeffective and time-efficient automated MCQ generation system. In this paper, the text is first summarized using the BERT algorithm, and accordingly sentence mapping is done for generating MCQs. In order to generate choices for the questions, distractors are generated using wordnet (A lexical database for English). As the BERT algorithm has much better performance over other legacy methods as well as it can process a large amount of data in less time, it will enhance the speed of generating MCQs from given text.

Figures (6)
3.1 Load raw text
3.1 Load raw text
BERT (Bidirectional Encoder Representations from Transformers) is a neural network-based technique for natural language processing. It is a pre-trained open-sourced model from Google. It helps computers to understand the language a bit more as humans do. The input text is summarized using the BERTSUM model, which is fine-tuned BERT for extractive summarization. The architecture of BERTSUM is shown in Fig- 2. In the BERTSUM model, at the start of each sentence, a [CLS] token is added, and between every two sentences, a [SEP] token is added to separate the sentences. Here, a [CLS] token is added to collect the preceding sentence context. Now each word of the sentence is tokenized using token embeddings. There is also a difference in segment embeddings. In the BERTSUM model, each sentence is assigned an embedding of Ea or Eb depending on whether the sentence is even or odd. If the sequence is [s1, s2, s3] then the segment embeddings are [Ea, Eb, Ea]. This way, all sentences are embedded and sent into further layers. BERTSUM assigns scores to each sentence that represents how much value that sentence adds to the overall document. So, [s1, s2, s3] is assigned [score1, score2, score3]. The sentences with the highest scores are then collected and rearranged to summarise the input text. In the output, the precise and summarized text is generated.
BERT (Bidirectional Encoder Representations from Transformers) is a neural network-based technique for natural language processing. It is a pre-trained open-sourced model from Google. It helps computers to understand the language a bit more as humans do. The input text is summarized using the BERTSUM model, which is fine-tuned BERT for extractive summarization. The architecture of BERTSUM is shown in Fig- 2. In the BERTSUM model, at the start of each sentence, a [CLS] token is added, and between every two sentences, a [SEP] token is added to separate the sentences. Here, a [CLS] token is added to collect the preceding sentence context. Now each word of the sentence is tokenized using token embeddings. There is also a difference in segment embeddings. In the BERTSUM model, each sentence is assigned an embedding of Ea or Eb depending on whether the sentence is even or odd. If the sequence is [s1, s2, s3] then the segment embeddings are [Ea, Eb, Ea]. This way, all sentences are embedded and sent into further layers. BERTSUM assigns scores to each sentence that represents how much value that sentence adds to the overall document. So, [s1, s2, s3] is assigned [score1, score2, score3]. The sentences with the highest scores are then collected and rearranged to summarise the input text. In the output, the precise and summarized text is generated.
3.3.3 Scoring and selecting words , International Research Journal of Engineering and Technology (IRJET) _ e- T Volume: 08 Issue: 05 | May 2021 www.irjet.net p- After creating a word co-occurrence matrix, RAKE calculates the keyword score. This score of candidate word is computed by taking the degree of a word in the matrix (i.e. the sum of the number of co-occurrences the word has with any other content word in the text), as the word frequency (i.e. the number of times the word appears in the text) which is given by,
3.3.3 Scoring and selecting words , International Research Journal of Engineering and Technology (IRJET) _ e- T Volume: 08 Issue: 05 | May 2021 www.irjet.net p- After creating a word co-occurrence matrix, RAKE calculates the keyword score. This score of candidate word is computed by taking the degree of a word in the matrix (i.e. the sum of the number of co-occurrences the word has with any other content word in the text), as the word frequency (i.e. the number of times the word appears in the text) which is given by,
If we were to compute the keyword score for phrases we will get as following: If we were to compute the keyword score for each words in our example, we will get as following:
If we were to compute the keyword score for phrases we will get as following: If we were to compute the keyword score for each words in our example, we will get as following:
Table -1: Test set results on the CNN/DailyMail dataset using ROUGE F1 The results and accuracy of the proposed system are comparatively higher than other systems. For the summarizer, we have used the BERTSUM model, which outperforms the other models. As shown in Table- 1 [8], all BERT-based models outperformed previous state-of-the-art models by a large margin. BERTSUM with Transformer achieved the best performance on all three metrics. The BERTSUM with LSTM model does not have an obvious influence on the summarization performance than the Classifier model. So among all the models, we have chosen BERTSUM + Transformer model, for the text summarization which has the best score compared to all the previously proposed systems. which has the best score compared to all the previously
Table -1: Test set results on the CNN/DailyMail dataset using ROUGE F1 The results and accuracy of the proposed system are comparatively higher than other systems. For the summarizer, we have used the BERTSUM model, which outperforms the other models. As shown in Table- 1 [8], all BERT-based models outperformed previous state-of-the-art models by a large margin. BERTSUM with Transformer achieved the best performance on all three metrics. The BERTSUM with LSTM model does not have an obvious influence on the summarization performance than the Classifier model. So among all the models, we have chosen BERTSUM + Transformer model, for the text summarization which has the best score compared to all the previously proposed systems. which has the best score compared to all the previously
Table -1: Results of Hypernym Validation 5. Conclusion & Future scope Multiple Choice Questions (MCQs) are generated successfully. Efficient questions are produced with good quality distractors. The problem of manually creating questions is solved with the proposed system. The proposed system creates automated questions with the help of NLP that reduces human intervention and it is a cost and time- effective system. And the accuracy of the distractor generated is reasonably high. This system not only helps teachers with E-assessments but also helps students who are preparing for competitive exams. Students can test their ability to solve the questions and can also check their understanding of the concepts. For generating distractors, the wordnet approach is used We evaluate the quality of wordnet by examining the validity of its constituent synonyms and its hypernym-hyponym pairs [9]. The hypernymy validation procedure was testec on the set of all direct hypernyms for noun synsets in the Princeton WordNet (v2.1). There are a total of 79297 hypernym-hyponym pairs constituting this set. The number of pairs validated by the algorithm at different steps of the approach is summarized in Table 2. In all, the algorithm was able to validate 56203 out of 79297 noun hypernym relation pairs in the Princeton Wordnet, giving a validatior percentage of 70.88%. Validation of the hypernym- hyponym relation for a pair of synsets is a strong indicator o: hypernym relation between them. However, the failure tc validate a synset pair is not a definitive indicator of erroneous construction and has to be treated as a flag for human inspection.
Table -1: Results of Hypernym Validation 5. Conclusion & Future scope Multiple Choice Questions (MCQs) are generated successfully. Efficient questions are produced with good quality distractors. The problem of manually creating questions is solved with the proposed system. The proposed system creates automated questions with the help of NLP that reduces human intervention and it is a cost and time- effective system. And the accuracy of the distractor generated is reasonably high. This system not only helps teachers with E-assessments but also helps students who are preparing for competitive exams. Students can test their ability to solve the questions and can also check their understanding of the concepts. For generating distractors, the wordnet approach is used We evaluate the quality of wordnet by examining the validity of its constituent synonyms and its hypernym-hyponym pairs [9]. The hypernymy validation procedure was testec on the set of all direct hypernyms for noun synsets in the Princeton WordNet (v2.1). There are a total of 79297 hypernym-hyponym pairs constituting this set. The number of pairs validated by the algorithm at different steps of the approach is summarized in Table 2. In all, the algorithm was able to validate 56203 out of 79297 noun hypernym relation pairs in the Princeton Wordnet, giving a validatior percentage of 70.88%. Validation of the hypernym- hyponym relation for a pair of synsets is a strong indicator o: hypernym relation between them. However, the failure tc validate a synset pair is not a definitive indicator of erroneous construction and has to be treated as a flag for human inspection.

Related papers

Automatic Multiple Choice Question Generation From Text: A Survey
DR. DHAWALESWAR RAO CH

IEEE Transactions on Learning Technologies, 2019

Automatic Multiple Choice Question (MCQ) generation from a text is a popular research area. MCQs are widely accepted for large-scale assessment in various domains and applications. However, manual generation of MCQs is expensive and time-consuming. Therefore, researchers were attracted towards automatic MCQ generation since the late 90's. Since then, many systems have been developed for MCQ generation. We perform a systematic review of those systems. This paper presents our findings on the review. We outline a generic workflow for an automatic MCQ generation system. The workflow consists of six phases. For each of these phases, we find and discuss the list of techniques adopted in the literature. We also study the evaluation techniques for assessing the quality of the system generated MCQs. Finally, we identify the areas where the current research focus should be directed toward enriching the literature.

View PDFchevron_right
Automating question generation from educational text
Ayan Bhowmick

arXiv (Cornell University), 2023

The use of question-based activities (QBAs) is wide-spread in education, traditionally forming an integral part of the learning and assessment process. In this paper, we design and evaluate an automated question generation tool for formative and summative assessment in schools. We present an expert survey of one hundred and four teachers, demonstrating the need for automated generation of QBAs, as a tool that can significantly reduce the workload of teachers and facilitate personalized learning experiences. Leveraging the recent advancements in generative AI, we then present a modular framework employing transformer based language models for automatic generation of multiple-choice questions (MCQs) from textual content. The presented solution, with distinct modules for question generation, correct answer prediction, and distractor formulation, enables us to evaluate different language models and generation techniques. Finally, we perform an extensive quantitative and qualitative evaluation, demonstrating trade-offs in the use of different techniques and models.

View PDFchevron_right
Automated Context-based Question-Distractor Generation using Extractive Summarization
IRJET Journal

IRJET, 2022

Multiple Choice Question (MCQ) is a versatile question type where respondents select one correct answer from the other choices. Generation of such MCQs along with different implausible options is tedious and time-consuming work. Existing automated question generation systems reduce manual efforts to some extent as they were at only sentence level information. By looking widespread usage of MCQs from school exams to competitive exams, automated generation of more reliable questions is required. The proposed system generated questions based on an Extractive summary using the BERT model which holds paragraphlevel context. BLEU score is used as an evaluation matrix to demonstrate the quality of model-generated questions across the human generated questions. The achieved BLEU score is 0.66. Though the proposed system focuses on Fill-inthe-blank questions scope can be extended to various different types of objective questions.

View PDFchevron_right
A Survey on Automated Assessment Questions Generation System Using Supervised Algorithms
IJRASET Publication

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

The only method for gauging the effectiveness of a teacher's lessons and the learning results of students is examination. Creating the questions and then randomly assigning them to the test are processes in the manual production of test papers. It takes a lot of time and effort to manually create test papers that match the standards of a good test paper. Mainly generating the test papers to evaluate the student technical skills is more time taking and the recruiters always want to know the students in better way by conducting the tests in the technical concepts. Our system helps in generating the questions automatically from the database which consists of the questions of the various technical concepts. To store the data and access the information from the database we are using MYSQL. To generate the test paper with the questions based on the skills known by the candidates we are using the classification algorithm like Naive Bayes Classifier, Random Forest Classifier and the Decision Tree. Naive Bayes, Random forest and Decision tree ,all are supervised algorithms. Giving the questions depending upon the candidate skills in the test paper will effectively evaluate the knowledge of the candidate in the skills that they know rather than testing their knowledge in completely unknown domain, the recruiters will also get the chance to know the candidate capabilities accurately and they can use the skills of the candidates in the better way and they can allocate the work to the candidates based on their performance in the particular skill. To know the performance of the candidate in the test , we have provided the graphical user interface (GUI) which was designed using the HTML and CSS concepts, where the questions are generated depending upon the classified results of the candidates.

View PDFchevron_right
A computer-aided environment for generating multiple-choice test items
Ruslan Mitkov

Natural Language Engineering, 2006

This paper describes a novel computer-aided procedure for generating multiple-choice test items from electronic documents. In addition to employing various Natural Language Processing techniques, including shallow parsing, automatic term extraction, sentence transformation and computing of semantic distance, the system makes use of language resources such as corpora and ontologies. It identifies important concepts in the text and generates questions about these concepts as well as multiple-choice distractors, offering the user the option to post-edit the test items by means of a user-friendly interface. In assisting test developers to produce items in a fast and expedient manner without compromising quality, the tool saves both time and production costs.

View PDFchevron_right
Automatic computer science domain multiple-choice questions generation based on informative sentences
farah maheen

PeerJ Computer Science

Students require continuous feedback for effective learning. Multiple choice questions (MCQs) are extensively used among various assessment methods to provide such feedback. However, manual MCQ generation is a tedious task that requires significant effort, time, and domain knowledge. Therefore, a system must be present that can automatically generate MCQs from the given text. The automatic generation of MCQs can be carried out by following three sequential steps: extracting informative sentences from the textual data, identifying the key, and determining distractors. The dataset comprising of various topics from the 9th and 11th-grade computer science course books are used in this work. Moreover, TF-IDF, Jaccard similarity, quality phrase mining, K-means, and bidirectional encoder representation from transformers techniques are utilized for automatic MCQs generation. Domain experts validated the generated MCQs with 83%, 77%, and 80% accuracy, key generation, and distractor generatio...

View PDFchevron_right
IRJET- Automatic Question Generation from Text: A Survey
IRJET Journal

IRJET, 2021

Students ask questions to satisfy their never-ending questions for getting knowledge. To perform competently assessment of students on their major concepts they learned from the study material. Preparing a set of questions for assessment can be time-consuming for teachers while getting questions from external sources like assessment books or question banks might not be relevant to content studied by students. An example, students ask questions to learn more from their teachers, teachers ask questions to help themselves evaluate the performance of the students, and our day-today lives involve asking questions in conversations. To perform competently assessment of students on their major concepts they learned from the study material. Automatic Question Answer Generation (AQAG) is the technique for generating a correct set of questions and answers from a paragraph, which can be text. Automatic question-answer generation (AQAG) is very important for many educational institutes but yet challenging problems in NLP. It is defined as the task of generating syntactically correct sound, semantically perfect and relevant questions and answers from several input formats like text, paragraphs. Question-Answer generation can be useful in many domains such as online assessment, e-tutoring sessions, chatbot systems, search engines and healthcare for analysing mental health. AQAG has got great consideration from researchers in a field of data science engineering.

View PDFchevron_right
Computer-aided generation of multiple-choice tests
Lệ Hà

Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing -, 2003

This paper describes a novel computer-aided procedure for generating multiple-choice tests from electronic instructional documents. In addition to employing various NLP techniques including term extraction and shallow parsing, the program makes use of language resources such as a corpus and WordNet. The system generates test questions and distractors, offering the user the option to post-edit the test items.

View PDFchevron_right
Automatic Generation of Multiple-Choice Test Items from Paragraphs Using Deep Neural Networks
Ruslan Mitkov

Routledge eBooks, 2023

Multiple-choice tests are a popular form of objective assessment where respondents are asked to select only one answer from a list of choices and are extensively used in teaching, learning, and training but also market research, elections, and TV shows. Against the background of ubiquitous digitalization, there is a pressing need to find a more efficient way to automate the development and delivery of multiple-choice test items. With the manual construction of such tests being a time-consuming and labor-intensive task, the objective of this chapter is to find effective alternatives to the lengthy and demanding activity of constructing multiple-choice test items by employing state-of-the-art natural language processing (NLP) and deep learning (DL) techniques. pioneered the development of an NLP methodology for generating multiple-choice tests from educational textbooks. Their original methodology employed various NLP techniques including shallow parsing, automatic term extraction, sentence transformation and semantic distance computing, and language resources such as corpora and ontologies. The automatic construction of multiple-choice tests included the identification of important concepts in the text, the generation of questions about these concepts, as well as the selection of semantically close-to-the-correct-answer distractors. The tool developed on the basis of this methodology offered the option to post-edit the automatically produced test items in a user-friendly interface. The evaluation reported that in assisting test developers to construct test items in a significantly faster and expedient manner without compromising quality, the implemented tool saved both time and production costs. While Mitkov and Ha's study has been well received by the field, it also has limitations, one of them being that each multiple-choice test item is generated from a single sentence. Our next challenge was to develop a methodology and tool capable of generating the questions of multiple-choice test items from the information contained in a paragraph of several sentences, not just a single sentence. In this chapter, we report on our experiments with the latest DL techniques seeking to achieve this objective. The generation of multiple-choice questions (MCQs) from more than one sentence is a significant breakthrough given that all previous related work had attempted generation from one sentence only. 1

View PDFchevron_right
Automatic Generation of English Language Test Questions Using Mathematica
Olga Rahneva

CBU International Conference Proceedings, 2017

This paper describes a computer algebra-aided generation of two types of English language tests, which further develops our recent work in this domain. The computer algebra system Wolfram Mathematica significantly advances the process of English language testing and assessment. The automatic generation of questions allows us to create a large set of equivalent questions of a certain topic based on a small amount of input values. This reduces authoring time during test creation, avails application of equal criteria and a fair assessment, and decreases the influence of subjective factors. In our previous work, we proposed methods for automatic generation of English language test questions. These were aimed at evaluating the students’ knowledge of lexical and grammatical structures found in the text using test questions that involved matching words and their meaning, matching parts of the whole, and finding synonyms, antonyms, and generalizations or specializations of words. This paper...

View PDFchevron_right

References (10)

  1. Santhanavijayan, A., Balasundaram, S.R., Hari Narayanan, S., Vinod Kumar, S., and Vignesh Prasad, V. (2017) 'Automatic generation of multiple-choice questions for e-assessment', Int. J. Signal and Imaging Systems Engineering, Vol. 10, Nos. 1/2, pp.54-62.
  2. Ayako Hoshino and Hiroshi Nakagawa (2005) " A real- time multiple-choice question generation for language testing: A preliminary study", EdAppsNLP 05: Proceedings of the second workshop on Building Educational Applications Using NLP.
  3. D. R. CH and S. K. Saha, "Automatic Multiple Choice Question Generation From Text: A Survey," in IEEE Transactions on Learning Technologies, vol. 13, no. 1, pp. 14-25, 1 Jan.-March 2020, doi: 10.1109/TLT.2018.2889100.
  4. Deepshree S. Vibhandik, Rucha C. Samant "Automatic / Smart Question Generation System for Academic Purpose", International Journal of Emerging Trends & Technology in Computer Science (IJETTCS), Volume 4, Issue 4, July -August 2015.
  5. Susanti, Y., Tokunaga, T., Nishikawa, H. et al. "Automatic distractor generation for multiple-choice English vocabulary questions", RPTEL 13, 15 (2018). https://doi.org/10.1186/s41039-018-0082-z.
  6. Mojitha Mohandas1, Aishwarya Chavan2, Rasika Manjarekar3, Divya Karekar4 (2015)"AUTOMATED QUESTION PAPER GENERATOR SYSTEM" International Journal of Advanced Research in Computer and Communication Engineering Vol. 4, Issue 12, December 2015 ISSN (Online) 2278-1021 ISSN (Print) 2319 5940.
  7. A. Y. Satria and T. Tokunaga, "Automatic generation of English reference question by utilising nonrestrictive relative clause", Proc. 9th Int. Conf. Comput. Supported Edu., pp. 379386, 2017.
  8. Yang Liu,"Fine-tune BERT for Extractive Summarization", arXiv:1903.10318v2 [cs.CL] 5 Sep 2019.
  9. Raghuvar Nadig, J. Ramanand, Pushpak Bhattacharyya, "Automatic Evaluation of Wordnet Synonyms and Hypernyms", Proceedings of ICON-2008.
  10. Rahim, T. N. T. A., Aziz, Z. A., Rauf, R. H. A., & Shamsudin, N. (2017). Automated exam question generator using genetic algorithm. 2017 IEEE Conference on e-Learning, e-Management and e-Services (IC3e).

Related papers

Automatic MCQ Generator Using Natural Language Techniques
IOSR Journals

Background: Multiple choice question (MCQ) generation from a text is a popular research area. They are widely used for a learner's knowledge assessment in the education sector. Manual generation of Mcq is hard, time-consuming and expensive. We have developed a system using various applications of Natural Language Processing Techniques. In this paper, we present a set of MCQs (Multiple Choice Questions) generated for any given input text along with a set of distractors and the correct answer to the question. In addition, The BERT(Bidirectional Encoder Representations from Transformers) model is used to generate a summary of the input text. The RAKE (Random Automatic Keyword Extraction) technique is used for extracting the keyword from the generated summary. This keyword is used as a parameter to generate questions as well as distractors for the MCQs.Distractors are the options that are generated apart from the correct answer. For the generation of MCQ, the wordnet and conceptnet algorithms are used. For the question generation, a T5 Transformer Model is trained using the encoder-decoder architecture. For the generation of MCQ, the wordnet and conceptnet algorithms are used. The final result has is a combination of questions with four options and a correct answer. Materials and Methods: In this study , The system will start with a prompt to provide an input file as a text document file .A description box will be available which will give information about the working of the software. Once the user enters the texts file , they will immediately get a list of multiple choice questions along with correct answer. The text file will be converted into a summary using the summarizer. The summary will be a single paragraph. The keywords will be extracted from the summary using RAKE. The Raw Automatic Keyword Extractor will generate mcq using the graph technique of natural language processing. Once the keyword is extracted the summary and the keyword will be provided as an input to the question Generation model. The question generation model will provide a set of questions on the basis of keywords and the summary provided. The keyword that is associated with the question will be used for distractor generation.The distractor generator will be done using conceptnet and wordnet. The final result will be a list of mcqs with correct answer under each question. Results: The final result will be a set of Multiple choice questions with a set of distractors and a correct answer to the question. Conclusion: The basic motivation of creating this desktop application were examinations attempted during Covid-19 pandemic which were inefficient. This system tends to overcome many flaws that the previous application sustained. The system summarizes the text and generates MCQs with distractors and right answer with probably higher accuracy.

View PDFchevron_right
Comparative analysis of NLP-driven MCQ generators from text sources
Richárd Németh, Asmae Azzi

Computers & Education: Artificial Intelligence, 2025

The application of learning sciences with technology has been shown to boost learner interactions, yet the potential of advanced tool, particularly those that leverage Natural Language Processing (NLP), still very much untapped in learning contexts. This paper speaks to this age-old problem of generating quality Multiple-Choice questions (MCQs)-a prevalent but time-consuming mode of assessmentvia the suggested comprehensive comparison study of template-based AI solutions. The study contrasts general-purpose Large Language Models (LLMs) with specialized MCQ-focused AI programs. The scientific approach employed was quite stringent, where each of the software applications was benchmarked using a common dataset of text across varying levels of complexity and topic. Results indicate that general-purpose LLMs, especially DeepSeek and ChatGPT, consistently present higher performance and reliability, especially when processing complex textual content. Whereas specialized tools offer distinctive formatting options, they exhibit decreasing performance as texts become more complex and signify strong operation constriction at the free versions. Developing solid and effective distractors turned out to be a complicated task for all the tested tools. We conclude the paper by presenting a standardized assessment model, making evidence-based recommendations for developers and teachers, and suggesting ways to incorporate various AI capabilities into modern educational assessment effectively.

View PDFchevron_right
A System for Generating Multiple Choice Questions: With a Novel Approach for Sentence Selection
Mukta Majumder

Multiple Choice Question (MCQ) plays a major role in educational assessment as well as in active learning. In this paper we present a system that generates MCQs automatically using a sports domain text as input. All the sentences in a text are not capable of generating MCQs; the first step of the system is to select the informative sentences. We propose a novel technique to select informative sentences by using topic modeling and parse structure similarity. The parse structure similarity is computed between the parse structure of an input sentence and a set of reference parse structures. In order to compile the reference set we use a number of existing MCQs collected from the web. Keyword selection is done with the help of occurrence of domain specific word and named entity word in the sentence. Distractors are generated using a set of rules and name dictionary. Experimental results demonstrate that the proposed technique is quite accurate.

View PDFchevron_right
An Automated Multiple-Choice Question Generation using Natural Language Processing Techniques
Ikechukwu E . Onyenwe

International Journal on Natural Language Computing, 2021

Automatic multiple-choice question generation (MCQG) is a useful yet challenging task in Natural Language Processing (NLP). It is the task of automatic generation of correct and relevant questions from textual data. Despite its usefulness, manually creating sizeable, meaningful and relevant questions is a time-consuming and challenging task for teachers. In this paper, we present an NLP-based system for automatic MCQG for Computer-Based Testing Examination (CBTE).We used NLP technique to extract keywords that are important words in a given lesson material. To validate that the system is not perverse, five lesson materials were used to check the effectiveness and efficiency of the system. The manually extracted keywords by the teacher were compared to the auto-generated keywords and the result shows that the system was capable of extracting keywords from lesson materials in setting examinable questions. This outcome is presented in a user-friendly interface for easy accessibility.

View PDFchevron_right
Automatic generation of fill‐in‐the‐blank question with corpus‐based distractors for e‐assessment to enhance learning
Sujan Kumar Saha

Computer Applications in Engineering Education, 2019

Knowledge acquisition is the prime objective of a learner from an educational system and evaluating the learner's knowledge is the eventual goal of an examination process. This paper introduces a system which is able to produce fill-in-the-blank questions to test the knowledge of a learner that he or she has accumulated after reading a course material. The question generation task is subdivided into three modules: sentence selection, answer-key identification and question formation along with distractors generation. The sentence is selected using a coarse-grain part-of-speech tagset. The answerkey is extracted by identifying topic-word in the sentence and question is formed by omitting this topic-word from the sentence. This paper also highlights an efficient corpus-based distractors generation technique to produce multiple-choice fill-in-the-blank test items.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved