Question Generation Research Articles

Facilitation of Student Questioning in the Malaysian Secondary Science Classroom Using the Investigable Questioning Formulation Technique (IQFT) Protocol

Abstract This study developed the Investigable Questioning Formulation Technique (IQFT) protocol to formulate investigable questions by following the procedures of design-based research. As guiding heuristics, the protocol used two provisional design principles based on teaching experience and previous studies that have applied tools for formulating questions, notably, the question formulation technique, SMART goals, and a typology of investigable and non-investigable questions. Two cycles comprising six lesson interventions were completed with two groups (n = 23, n = 25) of students in the same school in Malaysia. Questions were analyzed using qualitative content analysis and a question typology framework. Findings show the majority of students formulated comparison, exploratory, and validation of mental model questions. Some questions were posed in the prediction, descriptive, and problem-solving categories, but none were categorized as cause and effect, design and make, or pattern seeking. Implications for use of the IQFT protocol to help facilitate Malaysian students’ generation of investigable questions, design experiments, and implement open inquiry are discussed.

Correction to: Automatic generation of short-answer questions in reading comprehension using NLP and KNN

Correction to: Automatic generation of short-answer questions in reading comprehension using NLP and KNN

IDENTIFICATION OF THE IMPLEMENTATION OF EXAMINATION ASSESSMENT USING INTELLIGENCE QUESTION GENERATION OF TEST PAPER

The creation of the intelligence question can be helpful for understanding the concept for better knowledge. It can help with the information more efficiently and quickly which can help to understand the effectiveness of the students.The aim of the research is to know the impact of intelligence question generation on the tests of students. Primary methods of the research has been chosen for increasing the preciseness of work and this also includes the quantitative analysis and the process of SPSS. The number of participants included in the survey was 213 helping to analyze their viewpoint on the examination assessment process. The students are also helpful as they are analyzed with the help of some questions that may judge their learning process. The learning process is more personalized with the help of intelligence question generation. The satisfaction of students is also important as this automated question-generation process may generate the wrong questions out of the syllabus due to some faulty process of the system

Multi-hop Question Generation without Supporting Fact Information

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 with the goal of producing increasingly elaborate 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 and human evaluation, and show an improvement over the previous works.

Multi-Hop Question Generation with Knowledge Graph-Enhanced Language Model

The task of multi-hop question generation (QG) seeks to generate questions that require a complex reasoning process that spans multiple sentences and answers. Beyond the conventional challenges of what to ask and how to ask, multi-hop QG necessitates sophisticated reasoning from dispersed evidence across multiple sentences. To address these challenges, a knowledge graph-enhanced language model (KGEL) has been developed to imitate human reasoning for multi-hop questions.The initial step in KGEL involves encoding the input sentence with a pre-trained GPT-2 language model to obtain a comprehensive semantic context representation. Next, a knowledge graph is constructed using the entities identified within the context. The critical information in the graph that is related to the answer is then utilized to update the context representations through an answer-aware graph attention network (GAT). Finally, the multi-head attention generation module (MHAG) is performed over the updated latent representations of the context to generate coherent questions. Human evaluations demonstrate that KGEL generates more logical and fluent multi-hop questions compared to GPT-2. Furthermore, KGEL outperforms five prominent baselines in automatic evaluations, with a BLEU-4 score that is 27% higher than that of GPT-2.

Helpfulness of Question Prompt Sheet for Patient-Physician Communication Among Patients With Advanced Cancer

There are few robust evaluations of disease-specific question prompt sheets (QPS) in patient-physician communication among patients with advanced cancer. To compare the patient perception of helpfulness, global evaluation, and preference for the QPS vs a general information sheet (GIS), and to examine the effect of the QPS on participants' anxiety, participants' speaking time, number of questions asked, and length of the clinical encounter. This controlled, double-blind randomized clinical trial was conducted at an outpatient palliative and supportive care clinic in a cancer center in the US. Eligible patients were 18 years or older, had a cancer diagnosis, and were undergoing their first outpatient consultation visit with a palliative care physician from September 1, 2017, to May 31, 2019. Data analysis used a modified intention-to-treat design. Data were analyzed from May 18 to June 27, 2022. QPS, a 25-item list of questions developed by expert palliative care clinicians using a Delphi process and tested among ambulatory advanced cancer patients. The control was GIS, generic information material given routinely to patients seen at the supportive care clinic. The main outcome was patient perception of helpfulness. Secondary outcomes included global evaluation and preference of QPS compared with GIS immediately after the encounter. A total of 130 patients (mean [SD] age, 58.6 [13.3] years; 79 [60.8%] female) were randomized to receive either QPS (67 patients [51.5%]) or GIS (63 patients [48.5%]). Patients considered QPS and GIS equally helpful, with no statistically significant difference (mean [SD] helpfulness score, 7.2 [2.3] points vs 7.1 [2.7] points; P = .79). The QPS group, compared with the GIS group, had a higher global positive view of the material (mean [SD] global perception score, 7.1 [1.3] vs 6.5 [1.7]; P = .03) and felt it prompted them more to generate new questions (mean [SD] rating, 7.0 [2.9] vs 5.3 [3.5]; P = .005). Of 47 patients asked their preference between the items, more participants preferred the QPS to the GIS in communicating with their physicians (24 patients [51.1%] vs 7 patients [14.9%]; P = .01) at the 4-week follow-up. No significant differences between the QPS and GIS groups were observed regarding participant anxiety, speaking time, number of questions asked, or consultation length (eg, mean [SD] anxiety rating, 2.3 [3.7] vs 1.6 [2.7]; P = .19). In this randomized clinical trial, participants perceived both QPS and GIS as equally helpful, but they had a more positive global view of and preferred the QPS. QPS facilitated generation of new questions without increasing patient anxiety nor prolonging the consultation. The findings provide support for increased adoption and integration of QPS into routine oncologic care. ClinicalTrials.gov Identifier: NCT03287492.

A Mixed Study on the Factors for Enhancing Communication Competency of Nursing Students Participating in Multicultural Basic Subject Class

This study explores the factors that improve the communication competence of nursing students who participated in a basic subject class related to multicultural education, focusing on a particular medium. For this purpose, the students enrolled in a basic subject class of multicultural education at A University were selected as the research subjects. The research participants were 47 nursing students who participated in this class, and it was conducted as a mixed study. This class is conducted in a ‘flipped’ learning manner, and was established to cultivate communication competencies from the perspective of inter-cultural communication based on question generation and conversation. The results of the survey showed that interpretation competence, role performance competence, and self-presentation competence improved significantly on a statistical basis after the class. Although goal setting competence and message conversion competence were not significant among the students, their scores increased after they took the class. The researcher collected data through participatory observation, from the learners' task performance results, and through FGI analysis (what does this stand for?). The results of analyzing the data are as follows. First, the activity of generating questions in small groups was linked to new meaning-creating communication competencies. Second, communication is not simply a matter of information exchange efficiency, but is promoted more in the relationship of teamwork and cooperation. Third, communication competency for the students improved during the process of them reaching an agreement through conversation in a practical sense. Finally, a practical teaching method was proposed to improve their communication competency and to expand and apply these methods to their real lives.

Focusing on Digital Research Priorities for Advancing the Access and Quality of Mental Health

Digital mental health solutions are now well recognized as critical to solving the global mental health crisis. As research accelerates, it is now clear that solutions ranging from computer-based therapy programs to virtual reality headsets and smartphone apps to large language model chatbots are of interest, feasible, and hold exciting potential to improve mental health. This research should now consider the next generation of scientific and clinical questions regarding if these new approaches are equitable, valid, effective, implementable, efficacious, and even cost-effective. This paper outlines several of the new frontiers for the next generation of research and introduces JMIR Publications' partnership with the Society of Digital Psychiatry to further advance these aims.

Incremental Question Paper Generator

Exams are getting digitized all over the world. Basically, meaning that the traditional paper-based tests are being replaced by the certain computer-based tests which have proven to be both more consistent in allocating marks and faster than teacher correcting papers. The traditional exams usually consisted of subjective answers which were not the best way of grading the student’s perception of the subject. Hence, we are developing a computer-based system that will generate MCQ based question that will be better suited to grade students academically. So, Incremental Question Paper Generator (IQPG) is an attempt at developing a software which can implement adaptive evaluation along with generation of questions on its own. The software aims to generate an increasingly difficult or easy in simpler words, it aims to generate a question paper which dynamically changes the difficulty of its questions. Along the same the software generates these questions by learning from a pre-made dataset of questions.

Incremental Question Paper Generator

Exams are getting digitized all over the world. Basically, meaning that the traditional paper-based tests are being replaced by the certain computer-based tests which have proven to be both more consistent in allocating marks and faster than teacher correcting papers. The traditional exams usually consisted of subjective answers which were not the best way of grading the student’s perception of the subject. Hence, we are developing a computer-based system that will generate MCQ based question that will be better suited to grade students academically. So, Incremental Question Paper Generator (IQPG) is an attempt at developing a software which can implement adaptive evaluation along with generation of questions on its own. The software aims to generate an increasingly difficult or easy in simpler words, it aims to generate a question paper which dynamically changes the difficulty of its questions. Along the same the software generates these questions by learning from a pre-made dataset of questions

AUTOMATIC QUESTION GENERATION SYSTEM BASED NATURAL LANGUAGE PROCESSING USING PYTHON

Natural Language Processing has seen a surge in research on Automatic Question Generation (AQG) in recent times. AQG has proven to be an effective tool for Computer-Assisted Assessments by reducing the costs of manual question construction and generating a continuous stream of new questions. These questions are usually in the format of "WH" or reading comprehension type questions. To ensure natural and diverse questions, they must be semantically distinct based on their assessment level while maintaining consistency in their answers. This is particularly crucial in industries like education and publishing. In our research paper, we introduce a novel approach for generating diverse question sequences and answers using a new module called the "Focus Generator". This module is integrated into an existing "encoder-decoder" model to guide the decoder in generating questions based on selected focus contents. To generate answer tags, we employ a keyword generation algorithm and a pool of candidate focus from which we select the top three based on their level of information. The selected focus content is then utilized to generate semantically distinct questions.

Automatic generation of short-answer questions in reading comprehension using NLP and KNN.

In general, making evaluations requires a lot of time, especially in thinking about the questions and answers. Therefore, research on automatic question generation is carried out in the hope that it can be used as a tool to generate question and answer sentences, so as to save time in thinking about questions and answers. This research focuses on automatically generating short answer questions in the reading comprehension section using Natural Language Processing (NLP) and K-Nearest Neighborhood (KNN). The questions generated use article sources from news with reliable grammar. To maintain the quality of the questions produced, machine learning methods are also used, namely by conducting training on existing questions. The stages of this research in outline are simple sentence extraction, problem classification, generating question sentences, and finally comparing candidate questions with training data to determine eligibility. The results of the experiment carried out were for the Grammatical Correctness parameter to produce a percentage of 59.52%, for the Answer Existence parameter it yielded 95.24%, while for the Difficulty Index parameter it produced a percentage of 34.92%. So that the resulting average is 63.23%. So, this software deserves to be used as an alternative to automatically create reading comprehension questions.

Global research priorities related to the World Health Organization Labour Care Guide: results of a global consultation

BackgroundThe World Health Organization (WHO) published the WHO Labour Care Guide (LCG) in 2020 to support the implementation of its 2018 recommendations on intrapartum care. The WHO LCG promotes evidence-based labour monitoring and stimulates shared decision-making between maternity care providers and labouring women. There is a need to identify critical questions that will contribute to defining the research agenda relating to implementation of the WHO LCG.MethodsThis mixed-methods prioritization exercise, adapted from the Child Health and Nutrition Research Initiative (CHNRI) and James Lind Alliance (JLA) methods, combined a metrics-based design with a qualitative, consensus-building consultation in three phases. The exercise followed the reporting guideline for priority setting of health research (REPRISE). First, 30 stakeholders were invited to submit online ideas or questions (generation of research ideas). Then, 220 stakeholders were invited to score "research avenues" (i.e., broad research ideas that could be answered through a set of research questions) against six independent and equally weighted criteria (scoring of research avenues). Finally, a technical working group (TWG) of 20 purposively selected stakeholders reviewed the scoring, and refined and ranked the research avenues (consensus-building meeting).ResultsInitially, 24 stakeholders submitted 89 research ideas or questions. A list of 10 consolidated research avenues was scored by 75/220 stakeholders. During the virtual consensus-building meeting, research avenues were refined, and the top three priorities agreed upon were: (1) optimize implementation strategies of WHO LCG, (2) improve understanding of the effect of WHO LCG on maternal and perinatal outcomes, and the process and experience of labour and childbirth care, and (3) assess the effect of the WHO LCG in special situations or settings. Research avenues related to the organization of care and resource utilization ranked lowest during both the scoring and consensus-building process.ConclusionThis systematic and transparent process should encourage researchers, program implementers, and funders to support research aligned with the identified priorities related to WHO LCG. An international collaborative platform is recommended to implement prioritized research by using harmonized research tools, establishing a repository of research priorities studies, and scaling-up successful research results.

Commentary

Commentary

Leveraging well-formedness and cognitive level classifiers for automatic question generation on Java technical passages using T5 transformer

Leveraging well-formedness and cognitive level classifiers for automatic question generation on Java technical passages using T5 transformer

Automated Question Generator using NLP

Abstract: The purpose of the Automated Paper Generator is to automatize the winning guide machine with the aid of the help of computerized gadgets and full-fledged laptop code, pleasurable their requirements, simply so their precious facts/data can be maintained for an extended quantity with clean gaining access to and manipulation of the desired software program and hardware are honestly available on the market and easy to discern with. automatic query Paper Generator, as represented above, will result in blunders loss, at ease, reliable, and brief control system. it can help the person to not forget their opportunity sports but rather to concentrate on file preserving. So, it's going to assist an organization in the higher utilization of sources. The enterprise will keep computerized records while not redundant entries. which means that one needn't be distracted by info it is now not applicable while having the ability to acquire the statistics. The goal is to automatize its existing guide gadget by way of the assistance of picked equipment and complete-fledged laptop software, pleasurable their requirements, just so their precious facts/statistics can be preserved for an extended quantity with sincere access to and manipulation of the equal. on the whole, the venture describes the manner to manipulate permanently overall performance and better offerings for the customers. Texts with capacity academic well-worth have ended up on the market through the net. however, the victimization of those new texts in lecture rooms introduces several challenges, one in every of which is that they typically lack compliance with physical activities and assessments. right here, we will be inclined to address part of this task by way of automating the creation of a specific form of assessment object and the use of various questions developing with taxonomies. specially, we concentrate on mechanically generating actual WH queries. Our purpose is to make an automatic gadget if you want to take as enter a text and flip out as output questions for assessing a reader's understanding of the records within the text. The questions would possibly then be supplied to a trainer, who would possibly pick and revise people who she or he judges to be beneficial.

A Novel Framework for the Generation of Multiple Choice Question Stems Using Semantic and Machine-Learning Techniques

Multiple Choice Questions (MCQs) are a popular assessment method because they enable automated evaluation, flexible administration and use with huge groups. Despite these benefits, the manual construction of MCQs is challenging, time-consuming and error-prone. This is because each MCQ is comprised of a question called the "stem", a correct option called the "key" along with alternative options called "distractors" whose construction demands expertise from the MCQ developers. In addition, there are different kinds of MCQs such as Wh-type, Fill-in-the-blank, Odd one out, and many more needed to assess understanding at different cognitive levels. Automatic Question Generation (AQG) for developing heterogeneous MCQ stems has generally followed two approaches: semantics-based and machine-learning-based. Questions generated via AQG techniques can be utilized only if they are grammatically correct. Semantics-based techniques have been able to generate a range of different types of grammatically correct MCQs but require the semantics to be specified. In contrast, most machine-learning approaches have been primarily able to generate only grammatically correct Fill-in-the-blank/Cloze by reusing the original text. This paper describes a technique for combining semantic-based and machine-learning-based techniques to generate grammatically correct MCQ stems of various types for a technical domain. Expert evaluation of the resultant MCQ stems demonstrated that they were promising in terms of their usefulness and grammatical correctness.

VideoDL: Video-Based Digital Learning Framework Using AI Question Generation and Answer Assessment

Assessing learners’ understanding and competency in video-based digital learning is time-consuming and very difficult for educators, as it requires the generation of accurate and valid questions from pre-recorded learning videos. This paper demonstrates VideoDL, a video-based learning framework powered by Artificial Intelligence (AI) that supports automatic question generation and answer assessment from videos. VideoDL comprises of various AI algorithms, and an interactive web-based user interface (UI) developed using the principles of human-centred design. Our empirical evaluation using real-world videos from multiple domains demonstrates the effectiveness of VideoDL.

Quinductor: A multilingual data-driven method for generating reading-comprehension questions using Universal Dependencies

AbstractWe propose a multilingual data-driven method for generating reading comprehension questions using dependency trees. Our method provides a strong, deterministic and inexpensive-to-train baseline for less-resourced languages. While a language-specific corpus is still required, its size is nowhere near those required by modern neural question generation (QG) architectures. Our method surpasses QG baselines previously reported in the literature in terms of automatic evaluation metrics and shows a good performance in terms of human evaluation.

An Approach for generating best possible questions from the given text using Natural Language Processing

A crucial ability for every person is the capacity to ask pertinent questions. By automating the process of question formation, an automatic question generator is able to decrease the time and effort needed for manual question creation. Along with benefitting educational institutions like schools and colleges, automated question generation can be used in chatbots and for automated tutoring systems. Question Generation is an area in NLP that is still under research for greater accuracy. Research work has been done in many languages too. The goal of an automatic question generator is to generate syntactically and semantically correct questions, valid according to the given input. The Bidirectional Encoder Representations from Transformers (BERT) model is one of the pre-trained models adopted to implement the same. Additionally, we used Python packages, including NLTK, Spacy, and PKE. To test our findings, we evaluated the validity and relevance of generated questions using human-level cognition and evaluation. We were successful in creating inquiries that adequately reflected several of the peculiarities of English so that a person might comprehend them.