A Review on Natural Language Processing based Automatic Question Generation

Automatic question generation from text or paragraph is a great challenging task which attracts broad attention in natural language processing. Because of the verbose texts and fragile ranking methods, the quality of top generated questions is poor. In this paper, we present a novel framework Automatic Chinese Question Generation (ACQG) to generate questions from text or paragraph. In ACQG, we use an adopted TextRank to extract key sentences and a template-based method to construct questions from key sentences. Then a multi-feature neural network model is built for ranking to obtain the top questions. The automatic evaluation result reveals that the proposed framework outperforms the state-of-the-art systems in terms of perplexity. In human evaluation, questions generated by ACQG rate a higher score.

Automatic question generator (AQG) technology is a system developed to create questions automatically from input in the form of text, images, and videos. AQG has been developed using various approaches such as natural language processing (NLP), statistical approaches, and other machine approaches. AQG has a very important role in the world of education, especially in independent education, because it can be used as a good evaluation medium for students. Utilizing AQG in independent education gives students full control to determine their learning. AQG turns learning into a more interactive experience by generating questions that can trigger critical thinking and problem-solving skills. AQG technology developed in independent learning will encourage students to respond actively to the material and understand concepts more deeply. Approximately 60% of research related to AQG has been conducted for assessment, 18% for knowledge acquisition, and the remainder for validation and other purposes. This research was conducted by conducting a comprehensive review of 63 articles related to AQG in education.

In the last few years, researchers in the field of e-learning and Natural Language Processing (NLP) have shown an increased interest in automatic question generation. However, little research has discussed the automatic evaluation of listening comprehension in multimedia learning. In this work, we present an automatic quiz generation for TED Talks video clips, called TED Quiz. TED Quiz generates multiple-choice questions in two question types, gist-content questions and detail questions. We use a graph-based algorithm, Lex Rank, to identify the most important part of a talk, as the main concept of a gist-content question. We also proposed an approach to distractor selection for detail question generation that generates grammatically correct but semantically wrong sentences as distractors. The experimental results demonstrated that the measured results from automatically generated questions are comparable with that from manually generated questions because their scores were significantly correlated. Moreover, most subjects agreed that the generated listening comprehension questions were of quality and usefulness.

Answering questions is one method to increase or measure understanding. However, creating relevant and answerable questions from the given context is not easy. Automatic Question Generation (AQG) is a part of Natural Language Processing (NLP) which can generate questions automatically from text input. Many studies related to AQG have been carried out but are still very limited in Indonesian texts, especially those that use the latest Transformer variations. This study proposes an AQG system that utilizes the latest power Transformer, the multilingual Text-to-Text Transfer Transformer (mT5). We fine-tune the mT5 model to extract answers from context and generate questions based on those answers. We use the Indonesian dataset extracted from the TyDiQA dataset and evaluate this model against the TyDiQA validation set using BLEU (BiLingual Evaluation Understudy) and ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metrics. This model achieved BLEU-1, BLEU-2, BLEU-3, BLEU-4, and ROUGE-L scores of 36.54, 28.24, 22.61, 18.44, and 39.57, respectively. Our model performs well and generates questions in understandable Indonesian with good word choice and grammar based on manual validation.

Automatic Question Generation (AQG) is essential in educational technology, enabling the creation of assessments, practice exercises, and intelligent tutoring systems. Although recent neural approaches have achieved promising results, they often lack interpretability and control, thereby limiting their use in structured educational contexts. To overcome these challenges, this study introduces a structurally modular, rule-based AQG framework that generates factoid questions from educational texts through explicit linguistic rules and deterministic transformations. The proposed framework draws on classical rule-based question generation methods and employs a two-stage algorithmic design that distinctly separates linguistic analysis from question generation. The first stage involves linguistic preprocessing, clause extraction, and auxiliary-verb determination to identify syntactically valid, question-worthy clauses. In the second stage, rule-based transformations generate various factoid question types, such as who, what, where, when, how many, and how much, followed by disambiguation, template-based surface real- ization, and validation. This separation enhances interpretability, extensibility, and control over rule execution. Unlike data-driven models, the proposed framework does not require annotated training data and avoids hallucination by relying on explicit syntactic and semantic patterns. The resulting system produces grammatically correct, semantically meaningful, and reproducible questions, making it well suited for educational and academic applications. The study demonstrates that carefully designed rule-based systems remain a viable and effective alternative for automatic question generation in controlled domains.

Computer programming is a complex field that requires rigorous practice in programming code writing and learning skills, which can be one of the critical challenges in learning and teaching programming. The complicated nature of computer programming requires an instructor to manage its learning resources and diligently generate programming-related questions for students that need conceptual programming and procedural programming rules. In this regard, automatic question generation techniques help teachers carefully align their learning objectives with the question designs in terms of relevancy and complexity. This also helps in reducing the costs linked with the manual generation of questions and fulfills the need of supplying new questions through automatic question techniques. This paper presents a theoretical review of automatic question generation (AQG) techniques, particularly related to computer programming languages from the year 2017 till 2022. A total of 18 papers are included in this study. one of the goals is to analyze and compare the state of the field in question generation before COVID-19 and after the COVID-19 period, and to summarize the challenges and future directions in the field. In congruence to previous studies, there is little focus given in the existing literature on generating questions related to learning programming languages through different techniques. Our findings show that there is a need to further enhance experimental studies in implementing automatic question generation especially in the field of programming. Also, there is a need to implement an authoring tool that can demonstrate designing more practical evaluation metrics for students.

Automatic questions and answers generated are challenging tasks that attract broad engagement. This paper presents an automatic question and answer generation from Thai sentences. We adopted question classification to predict the expected wh-question type before generating question and answer. This experimental study tested the question and answer generation on the sampling set of 300 Thai sentences based on the wh-question type that trained classify category from 15,000 samples. Automatic evaluation is performed on a reference set using the BLEU metrics and human evaluation. The experiment results show that the proposed method can generate questions and answers from Thai sentences. However, the performance based on the efficiency of Natural Language Processing includes tokenization, Named Entities Recognition, and Part of Speech tagging task because it could effectively extract focusing words correctly and suitable to answer the question that enhances the trustworthiness of future work in question and answer generation from Thai texts.KeywordsQuestion and answer generationAutomatic question generationNatural language processingThai sentences analysis

Manual construction of questions is a tedious and complicated process. Automatic Question Generation (AQG) methods work towards diminishing these costs and to fulfil the requirement for a persistent supply of new questions. Current AQG techniques utilize complicated architectures, that require intensive computational resources as well as a deeper understanding of the subject. In this paper we propose an end-to-end AQG system that utilises the power of a recently introduced transformer, the Text-to-Text Transfer Transformer (T5). We use the pre-trained T5 model and fine-tune it for our down-stream task of question generation. Our model performs very well on unseen data and generates well-formed and grammatically correct questions. These questions can be used directly by students, to examine their own level of understanding, and teachers, to quickly reinforce key concepts whenever required. The model has also been deployed in the form of a web application for public access. This application serves as an educational tool using which any individual can assess their knowledge and identify areas of improvement.

Educational automatic question generation (AQG) is often unable to realize its full potential in educational applications due to insufficient training data. For this reason, current research relies on noneducational question answering datasets for system training and evaluation. However, noneducational training data may comprise different language patterns than educational data. Consequently, the research question of whether models trained on noneducational datasets transfer well to the educational AQG task arises. In this work, we investigate the AQG subtask of answer selection, which aims to extract meaningful answers for the questions to be generated. We train and evaluate six modern and well-established BERT-based machine learning model architectures on two widely used noneducational datasets. Furthermore, we introduce a novel, midsized educational dataset for answer selection called TQA-A, which is used to investigate the transfer capabilities of the noneducational models to the educational domain. In terms of phrase-level evaluation metrics, noneducational models perform similar to models trained directly on the novel educational TQA-A dataset, although trained with considerably more training data. Moreover, models trained directly on TQA-A select fewer named entity-based and more verb-based answers than noneducational models. This provides evidence for differences in noneducational and educational answer selection tasks.

An automatic question generation (QG) system aims to produce questions from a text, such as a sentence or a paragraph. Traditional approaches are mainly based on heuristic, hand-crafted rules to transduce a declarative sentence to a related interrogative sentence. However, creating such a set of rules requires deep linguistic knowledge and most of these rules are language-specific. Although a data-driven approach reduces the participation of linguistic experts, to get sufficient labeled data for QG model training is still a difficult task. In this paper, we applied a neural sequence-to-sequence pointer-generator network with various transfer learning strategies to capture the underlying information of making a question, on a target domain with rare training pairs. Our experiment demonstrates the viability of domain adaptation in QG task. We also show the possibility that transfer learning is helpful in a semi-supervised approach when the amount of training pairs in the target QG dataset is not large enough.

Natural Language Processing (NLP) is now widely integrated into web and mobile applications, enabling natural interactions between humans and computers. Although there is a large body of NLP studies published in Information Systems (IS), a comprehensive review of how NLP research is conceptualised and realised in the context of IS has not been conducted. To assess the current state of NLP research in IS, we use a variety of techniques to analyse a literature corpus comprising 356 NLP research articles published in IS journals between 2004 and 2018. Our analysis indicates the need to move from semantics to pragmatics. More importantly, our findings unpack the challenges and assumptions underlying current research trends in NLP. We argue that overcoming these challenges will require a renewed disciplinary IS focus. By proposing a roadmap of NLP research in IS, we draw attention to three NLP research perspectives and present future directions that IS researchers are uniquely positioned to address.

The increased demand from people to learn Data Science, together with the arrival of the Coronavirus pandemic and the increase in home-office activities, teaching institutions in this area, has to expand online assistance systems to students. Since this assistance is not always restricted to a particular schedule, it produces instability in the daily tasks that teachers have to perform. To avoid this, this study implements a closed-domain Chatbot for Data Science that uses as a Question Answering System and works as an assistant to teachers in specific questions that students may have. In addition, it allows the students to check their knowledge in any related topic by the automatic generation of questions according to the chosen topic. The System also has an automatic correction process that compares the response given by the student with the correct one. Such features were implemented using the latest Deep Learning models oriented to Natural Language Processing (NLP), such as Transformers architectures. Although the response time is relatively long in some cases, it generated good answers as well as questions. In future works, the authors propose to optimize the system in terms of speed and quality of results. To this end, the reduction in the number of steps is required by the system, as well as finding more efficient solutions according to the research progress in NLP.

Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents. Many existing techniques generate questions by effectively looking at one sentence at a time, leading to questions that are easy and not reflective of the human process of question generation. Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. In order to link a broad document context to the target answer, we represent the relevant context via a multi-stage attention mechanism, which forms the foundation of a sequence to sequence model. We outperform state-of-the-art methods on question generation on three question-answering datasets - SQuAD, MS MARCO and NewsQA. 1

Machine learning techniques have long been the foundations of speech processing. Bayesian classiflcation, decision trees, unsupervised clustering, the EM algorithm, maximum entropy, etc. are all part of existing speech recognition systems. The success of statistical speech recognition has led to the rise of statistical and empirical methods in natural language processing. Indeed, many of the machine learning techniques used in language processing, from statistical part-of-speech tagging to the noisy channel model for machine translation have roots in work conducted in the speech fleld. However, advances in learning theory and algorithmic machine learning approaches in recent years have led to signiflcant changes in the direction and emphasis of the statistical and learning centered research in natural language processing and made a mark on natural language and speech processing. Approaches such as memory based learning, a range of linear classiflers such as Boosting, SVMs and SNoW and others have been successfully applied to a broad range of natural language problems, and these now inspire new research in speech retrieval and recognition. We have seen an increasingly close collaboration between voice and language processing researchers in some of the shared tasks such as spontaneous speech recognition and understanding, voice data information extraction, and machine translation. The purpose of this special issue was to invite speech and language researchers to communicate with each other, and with the machine learning community on the latest machine learning advances in their work. The call for papers was met with great enthusiasm from the speech and natural language community. Thirty six submissions were received; each paper was reviewed by at least three reviewers. Only ten papers were selected re∞ecting not only some of the best work on machine learning in the areas of natural language and spoken language processing but also what we view as a collection of papers that represent current trends in these areas of research both from the perspective of

Due to a boom in the amount of data generated every day, there is a need for automation in the education domain where it is humanly impossible for a single individual to make sense out of the data even for a simple task such as generating questions for a quiz or a test. Automatic question generation for textual inputs is valuable in academics where answering questions helps students to learn and improve their understanding of their field of study. Automatic question generation finds application in dialog systems or virtual assistants where asking questions is an important part of interactions between humans and machines. In this paper, we propose a state-of-the-art solution using a pipeline that utilizes natural language processing and image captioning techniques capable of generating questions not only for textual but also for visual inputs. Along with the question, distractors for the generated questions and their answers are also created.