Question Generation Through Transfer Learning

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.

The question generation task can automatically generate large-scale questions to provide training data for reading comprehension tasks and QA systems, which are crucial for low-resource languages such as Tibetan. At present, due to the emergence of large-scale datasets and pre-trained language models in the Chinese and English domains, the task of question generation in the Chinese and English domains has been well developed, while the research on question generation in the Tibetan is still in its infancy. The main reason is the lack of datasets and the relatively backward development of various models in Tibetan. To solve the above questions, this paper constructs a Tibetan pre-trained language model TiBERT to provide a basis for the development of various downstream tasks, to expand the datasets of Tibetan machine reading comprehension, this paper proposes a Tibetan question generation model named TQGR. The model consists of two parts, the question generation and question quality assessment. The question generation adopts the classic seq2seq architecture to generate questions, and the question quality assessment improves the quality of generated questions by evaluating the fluency reward score, word repetition rate reward score and interrogative words classification auxiliary task. Finally, the experimental results show that our model has higher performance than baseline models, and ablation experiments demonstrate the effectiveness of the three mechanism.

We study how to improve the performance of Question Answering over Knowledge Base (KBQA) by utilizing the factoid Question Generation (QG) in this paper. The task of question generation (QG) is to generate a corresponding natural language question given the input answer, while question answering (QA) is a reverse task to find a proper answer given the question. For the KBQA task, the answer could be regarded as a fact containing a predicate and two entities from the knowledge base. Training an effective KBQA system needs a lot of labeled data which are hard to acquire. And a trained KBQA system still performs poor when answering the questions corresponding with unseen predicates in the training process. To solve these challenges, we propose a unified framework to combine the QG and QA with the help of knowledge base and text corpus. The models of QA and QG are first trained jointly on the gold dataset, then the QA model is fine tuned by utilizing a supplemental dataset constructed by the QG model with the help of text evidence. We conduct experiments on two datasets SimpleQuestions and WebQSP with the Freebase knowledge base. Empirical results show that our framework improves the performance of KBQA and performs comparably with or even better than the state-of-the-arts.

NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning. Yet, QG systems have not been widely adopted in classrooms to date. In this work, we aim to pinpoint key impediments and investigate how to improve the usability of automatic QG techniques for educational purposes by understanding how instructors construct questions and identifying touch points to enhance the underlying NLP models. We perform an in-depth need finding study with 11 instructors across 7 different universities, and summarize their thought processes and needs when creating questions. While instructors show great interests in using NLP systems to support question design, none of them has used such tools in practice. They resort to multiple sources of information, ranging from domain knowledge to students' misconceptions, all of which missing from today's QG systems. We argue that building effective human-NLP collaborative QG systems that emphasize instructor control and explainability is imperative for real-world adoption. We call for QG systems to provide process-oriented support, use modular design, and handle diverse sources of input.

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.

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.

<span>The importance of automatic question generation (AQG) systems in education is recognized for automating tasks and providing adaptive assessments. Recent research focuses on improving quality with advanced neural networks and machine learning techniques. However, selecting the appropriate target sentences and concepts remains challenging in AQG systems. To address this problem, the authors created a novel system that combined sentence structure analysis, dependency parsing approach, and named entity recognition techniques to select the relevant target words from the given sentence. The main goal of this paper is to develop an AQG system using syntactic and semantic sentence structure analysis. Evaluation using manual and automatic metrics shows good performance on simple and short sentences, with an overall score of 3.67 out of 5.0. As the field of AQG continues to evolve rapidly, future research should focus on developing more advanced models that can generate a wider range of questions, especially for complex sentence structures.</span>

Question generation is the parallel task of question answering, where given an input context and, optionally, an answer, the goal is to generate a relevant and fluent natural language question. Although recent works on question generation have experienced success by utilizing sequence-to-sequence models, there is a need for question generation models to handle increasingly complex input contexts to produce increasingly detailed questions. Multi-hop question generation is a more challenging task that aims to generate questions by connecting multiple facts from multiple input contexts. In this work, we apply a transformer model to the task of multi-hop question generation without utilizing any sentence-level supporting fact information. We utilize concepts that have proven effective in single-hop question generation, including a copy mechanism and placeholder tokens. We evaluate our model’s performance on the HotpotQA dataset using automated evaluation metrics, including BLEU, ROUGE and METEOR and show an improvement over the previous work.

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

Visual Question Generation (VQG) is one of the most challenging problems since it aims to produce relevant and meaningful questions from images. As the VQG process is able to generate a diverse set of questions that do not exist in the training set, various models (e.g., visual question answering) can be beneficial from this question generation task by evaluating the model’s performance in unknown settings. In this paper, we explored the visual question generation task on images collected by an unmanned aerial vehicle (UAV). We highlight the significant role of the question generation task and present a variational attention-based model that focuses on creating diversified and meaningful questions from images. In comparison to baseline approaches, our presented method has demonstrated the ability to create a broad and meaningful set of questions.

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

The advent of the Internet resulted in availability of e-content in huge quantities; this e-content includes information in different domains. This information is being exploited for various reasons and applications. As the formal evaluation and assessment techniques are undergoing transformations, there is also a need for a voluminous Question Bank (QB). The manual creation of questions is a time-consuming and expensive task as it requires domain experts and there is a growing trend towards question bank based question paper generation for assessment. Hence the problem of automatic question generation has attracted attention of the Natural Language Processing (NLP) research community; this problem can be handled by NLP. Automatic generation of high-quality questions is the long-term goal of the Question Generation (QG) research community. The automatic question generation aims to generate all possible questions from the input text or document. This survey article presents the issues, challenges and approaches as well as reviews the reported research work in the context of automatic question generation for different languages at national and international level.

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.

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.

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.