Automatic Question Generation Research Articles

Semantic Question Generation Using Artificial Immunity

This research proposes an automatic question generation model for evaluating the understanding of semantic attributes in a sentence. The Semantic Role Labeling and Named Entity Recognition are used as a preprocessing step to convert the input sentence into a semantic pattern. The Artificial Immune System is used to build a classifier that will be able to classify the patterns according to the question type in the training phase. The question types considered here are the set of WH-questions like who, when, where, why, and how. A pattern matching phase is applied for selecting the best matching question pattern for the test sentence. The proposed model is tested against a set of sentences obtained from many sources such as the TREC 2007 dataset for question answering, Wikipedia articles, and English book of grade II preparatory. The experimental results of the proposed model are promising in determining the question type with classification accuracy reaching 95%, and 87% in generating the new question patterns.

Tapping into the Power of Automatic Question Generation

ABSTRACT Question Generation (QG) is an important element of learning environments, information seeking systems, help systems, and other applications. There are a number of distinct research subfields which are concerned with the Automatic Question Generation (AQG) Systems. This research tries to have a wide look on existing automatic question generation systems, and some trials of overcoming its difficulties from different points of views . General Terms Natural Language Processing, Natural Language Generation questions) whereas sha Keywords Automatic Question Generation, Questions Taxonomy, Multiple Choice Questions, Entity Based Questions. 1. INTRODUCTION Questions have been studied as part of the task of Question Answering in the field of Natural Language Processing (NLP). At the beginning, question answering research focused on answering questions from databases and knowledge representations [1], but in the past two decades has refocused on retrieving answers from text – e.g., in 1999 the evaluation of question-answering systems became part of the Text Retrieval Conference (TREC) series. Simultaneously, there has been a strand of research on advisory dialogue systems [2]. All the previous systems were primarily aimed at responding to the user’s questions. Recently, there has been a broader transformation in the field of Natural Language Processing researches in Question Generation task. Since 2008, researchers from different communities, such as, Discourse Analysis, Dialogue Modeling, Formal Semantics, Intelligent Tutoring Systems, Natural Language Generation, Natural Language Understanding, and Psycholinguistics, have met annually at the Question Generation workshop. AQG system would be useful for building an automated trainer for learners to ask better questions, and for building a better hint and question asking facilities in intelligent tutoring systems [3]. Another benefit of QG is that it can be a good tool to help in improving the quality of the Question Answering (QA) systems. Available studies revealed that humans were not very skilled in asking good questions. Therefore, they would benefit from automated QG systems to assist them in meeting their inquiry needs [4]. In this research, a survey about automatic question generation and different variety of work that has been done is discussed. The rest of the paper is organized as follows: section 2 discusses the basic steps for automatic question generation systems; section 3 introduces two distinct taxonomies of questions, section 4 the state of the art in which a description of the previous work, finally section 5 introduces a conclusion with some remarks.

Semantic Attributes Model for Automatic Generation of Multiple Choice Questions

this research, an automatic multiple choice question generation system for evaluating semantic role labels and named entities is proposed. The selection of the informative sentence and the keyword to be asked about are based on the semantic labels and named entities that exist in the question sentence. The research introduces a novel method for the distractor selection process. Distractors are chosen based on a string similarity measure between sentences in the data set. Eight algorithms of string similarity measures are used in this research. The system is tested using a set of sentences extracted from the data set for question answering. Experimental results prove that the semantic role labeling and named entity recognition approaches can be used for keyword selection. String similarity measures have been used in generating the distractors in the process of automatic multiple choice questions generation. Combining the similarity measures of some algorithms led to enhancing the results.

Functional Modules of a Semi-Automatic Question Generating System

In the last decade different applications of computer science (data mining, text mining) have been recognised. Presently an automatic question generation is a current research area. The elaborated system generates multi-choice questions from textbooks without using an external semantic database. Main demands made for the implemented automatic question generation system: supporting the Hungarian language, using a free grammar analytic, generating test questions from annotated texts, implementing potential answers from an internal, own developed semantic data base, supporting multi-choice problems, a possibility of implementing electronic and printable test papers. During planning the framework among the applied methods, clustering on the base of distances, a classification algorithm on the base of a neural net, in the case of generating questions and answer alternatives an own developed semantic data base was implemented. To prove the practical applicability of the automated question generating method, Java-language software was developed.

Automatic question generation for supporting argumentation

Given a discussion topic, students may sometimes not proceed with their argumentation. Can questions which are semantically related to a given discussion topic help students develop further arguments? In this paper, we introduce a technical approach to generating questions upon the request of students during the process of collaborative argumentation. The contribution of this paper lies in combining different NLP technologies and exploiting semantic information to support users develop their arguments in a discussion session via tailored questions of different types.

Automatic generation of multiple choice questions using dependency-based semantic relations

In this paper, we present an unsupervised dependency-based approach to extract semantic relations to be applied in the context of automatic generation of multiple choice questions (MCQs). MCQs also known as multiple choice tests provide a popular solution for large-scale assessments as they make it much easier for test-takers to take tests and for examiners to interpret their results. Manual generation of MCQs is a very expensive and time-consuming task and yet they often need to be produced on a large scale and within short iterative cycles. We approach the problem of automated MCQ generation with the help of unsupervised relation extraction, a technique used in a number of related natural language processing problems. The goal of Unsupervised relation extraction is to identify the most important named entities and terminology in a document and then recognise semantic relations between them, without any prior knowledge as to the semantic types of the relations or their specific linguistic realisation. We use these techniques to process instructional texts and identify those facts (terminology, entities, and semantic relations between them) that are likely to be important for assessing test-takers' familiarity with the instructional material. We investigate an approach to learn semantic relations between named entities by employing a dependency tree model. Our findings show that an optimised configuration of our MCQ generation system is capable of attaining high precision rates, which are much more important than recall in the automatic generation of MCQs. We also carried out a user-centric evaluation of the system, where subject domain experts evaluated automatically generated MCQ items in terms of readability, usefulness of semantic relations, relevance, acceptability of questions and distractors and overall MCQ usability. The results of this evaluation make it possible for us to draw conclusions about the utility of the approach in practical e-Learning applications.

Automatic Generation of Standard Examination Questions Based on Ontology

Examination question is one of the important tools that reflect students' learning situation and teachers' teaching effectiveness. Traditional questions were generated by the teacher manual, which will lead to the disadvantages of inefficient work and no reusable examination. In order to overcome these disadvantages, the paper proposes an ontology-based approach to standardized examination questions, which automatically generates questions and focuses on the multiple-option questions.

The Development of an Automatic Question Generation System on Facebook Using an Artificial Bee Colony Algorithm

Facebook is currently one of the world's most popular social networking services, and has been widely used in the field of e-learning. In general, learners in e-learning environments need to evaluate their learning ability through taking tests to present the learning achievement. In order to evaluate their ability on e-learning platform with social network services, this study proposes an automatic question generation system for individual learning status. The proposed system uses the artificial bee colony algorithm to find suitable questions for each learner according to the learner's profile, reading experience, professional ability, and the e-learning records in the system. The experimental results indicate that the proposed method improves the accuracy of the automatic question generation system and that it outperforms the random method.

Development of classification module for automated question generation framework

Automatic question generation is in the focus of recent researches which includes bordering disciplines like education, text mining, knowledge-engineering. The elaborated system generates multi-choice questions from textbooks without using an external semantic database. One of the base modules of the system is the classification module defining the extracted word. This paper describes modules of the framework including a detailed analysis of the classification part. We show the operability of the elaborated system through a practical test.

Automatic generation of analogy questions for student assessment: an Ontology-based approach

Different computational models for generating analogies of the form ‘‘A is to B as C is to D’’ have been proposed over the past 35 years. However, analogy generation is a challenging problem that requires further research. In this article, we present a new approach for generating analogies in Multiple Choice Question (MCQ) format that can be used for students’ assessment. We propose to use existing high-quality ontologies as a source for mining analogies to avoid the classic problem of hand-coding concepts in previous methods. We also describe the characteristics of a good analogy question and report on experiments carried out to evaluate the new approach.Keywords: e-assessment; ontology; analogy questions; relational similarity; vector space model; corpus-based evaluation(Published: 30 August 2012)http://dx.doi.org/10.3402/rlt.v20i0.19198

G-Asks: An Intelligent Automatic Question Generation System for Academic Writing Support

Many electronic feedback systems have been proposed for writing support. However, most of these systems only aim at supporting writing to communicate instead of writing to learn, as in the case of literature review writing. Trigger questions are potentially forms of support for writing to learn, but current automatic question generation approaches focus on factual question generation for reading comprehension or vocabulary assessment. This article presents a novel Automatic Question Generation (AQG) system, called G-Asks, which generates specific trigger questions as a form of support for students' learning through writing. We conducted a large-scale case study, including 24 human supervisors and 33 research students, in an Engineering Research Method course at The University of Sydney and compared questions generated by G-Asks with human generated question. The results indicate that G-Asks can generate questions as useful as human supervisors (`useful' is one of five question quality measures) while significantly outperforming Human Peer and Generic Questions in most quality measures after filtering out questions with grammatical and semantic errors. Furthermore, we identified the most frequent question types, derived from the human supervisors' questions and discussed how the human supervisors generate such questions from the source text.

Next generation of e-assessment: automatic generation of questions

This paper provides a review of the state-of-the-art in automatic assessment generation. The paper focuses on and further develops methods for automatic generation of assessments from ontologies. We describe a novel approach and evaluate it by comparing it to other existing approaches. In addition, we report on our experience to evaluate the generated questions using a corpus-based method to simulate a real student trying to solve the questions.

Automatic question generation from documents for e-learning

Question generation is an important module for e-learning systems. The task of manually extracting questions for each concept according to the cognitive level of the learner is a tiresome job. Automatic extraction of questions from documents for e-learning could simplify the task of assessing the students knowledge on the subject through questions that cover all the concepts learnt and of varying difficulty. To assess students according to their learning mental ability, questions in this work are matched with different levels of Blooms taxonomy. The generated questions are evaluated based on question evaluation metric and with the proposed domain and topic coverage measure.

Algorithms for Automatic Generation of Logical Questions on Mobile Devices

In this paper, we present algorithms for automatic generation of logic reasoning questions. The algorithms are able to construct questions that are solvable with unique solutions. The algorithms employ AI techniques such as semantic networks to produce verbal questions. These algorithms are small in size and are able to replace traditional question databases. They are particularly suitable for implementation on the memory constrained mobile platforms. The algorithms can be applied to question generation for job interview, civil service exam, etc.

Collaborative Writing Support Tools on the Cloud

Academic writing, individual or collaborative, is an essential skill for today's graduates. Unfortunately, managing writing activities and providing feedback to students is very labor intensive and academics often opt out of including such learning experiences in their teaching. We describe the architecture for a new collaborative writing support environment used to embed such collaborative learning activities in engineering courses. iWrite provides tools for managing collaborative and individual writing assignments in large cohorts. It outsources the writing tools and the storage of student content to third party cloud-computing vendors (i.e., Google). We further describe how using machine learning and NLP techniques, the architecture provides automated feedback, automatic question generation, and process analysis features.

An Automatic Question Generation Method for a Local Councilor Search System

This paper presents an automatic question generation method for a local councilor search system. Our purpose is to provide residents with information about local council activities in an easy-to-understand manner. Our designed system creates a decision tree with leaves that correspond to local councilors in order to clarify the differences in the activities of local councilors using local council minutes as the source. Moreover, our system generates questions for selecting the next branch at each condition in the decision tree. We confirmed experimentally that these questions are appropriate for the selection of branches in the decision tree.

Online testing, current issues and future trends

In this paper we analyze the state of art of the assessment of students’ knowledge through online tests. In particular, we describe the main functionalities currently implemented in the main existing online testing systems. Furthermore, we present a literary review of the most recently proposed techniques for using online tests in different application ambits, such as: Computerized Adaptive Testing (CAT), automatic question generation, log data analysis, m-learning and educational gaming.

Automatic testing and assessment of neuroanatomy using a digital brain atlas: Method and development of computer‐ and mobile‐based applications

Preparation of tests and student's assessment by the instructor are time consuming. We address these two tasks in neuroanatomy education by employing a digital media application with a three-dimensional (3D), interactive, fully segmented, and labeled brain atlas. The anatomical and vascular models in the atlas are linked to Terminologia Anatomica. Because the cerebral models are fully segmented and labeled, our approach enables automatic and random atlas-derived generation of questions to test location and naming of cerebral structures. This is done in four steps: test individualization by the instructor, test taking by the students at their convenience, automatic student assessment by the application, and communication of the individual assessment to the instructor. A computer-based application with an interactive 3D atlas and a preliminary mobile-based application were developed to realize this approach. The application works in two test modes: instructor and student. In the instructor mode, the instructor customizes the test by setting the scope of testing and student performance criteria, which takes a few seconds. In the student mode, the student is tested and automatically assessed. Self-testing is also feasible at any time and pace. Our approach is automatic both with respect to test generation and student assessment. It is also objective, rapid, and customizable. We believe that this approach is novel from computer-based, mobile-based, and atlas-assisted standpoints.

A Method for Automatic Generation of Multiple-Choice Questions Adapted to Students’ Understanding

A Method for Automatic Generation of Multiple-Choice Questions Adapted to Students’ Understanding

Automatic Generation of Prediction Questions during Program Visualization

Based on previous research, it seems that the activities performed by and the engagement of the students matter more than the content of the visualization. One way to engage students to interact with a visualization is to present them with prediction questions. This has been shown to be beneficial for learning. Based on the engagement taxonomy and benefits of the question answering during the algorithm visualization, we propose to implement an automatic question generation into a program visualization tool, Jeliot 3. In this paper, we explain how the automatic question generation can be incorporated into the current design of Jeliot 3. In addition, we provide various example questions that could be automatically generated based on the data obtained during the visualization process.