Semi-automatic Generation of Multiple-Choice Tests from Mentions of Semantic Relations

Ai, Renlong; Krause, Sebastian; Kasper, Walter; Xu, Fang; Uszkoreit, Hans

doi:10.18653/v1/w15-4405

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only two studies (Huang and He 2016;Ai et al 2015) have considered paraphrasing. Ai et al (2015) employed a manually created library that includes different ways to express particular semantic relations for this purpose. For instance, "wife had a kid from husband" is expressed as "from husband, wife had a kid".…”

Section: Verbalisationmentioning

confidence: 99%

A Systematic Review of Automatic Question Generation for Educational Purposes

Kurdi

Leo

Parsia

et al. 2019

Int J Artif Intell Educ

267

111

View full text Add to dashboard Cite

While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience, and resources. This, in turn, hinders and slows down the use of educational activities (e.g. providing practice questions) and new advances (e.g. adaptive testing) that require a large pool of questions. To reduce the expenses associated with manual construction of questions and to satisfy the need for a continuous supply of new questions, automatic question generation (AQG) techniques were introduced. This review extends a previous review on AQG literature that has been published up to late 2014. It includes 93 papers that were between 2015 and early 2019 and tackle the automatic generation of questions for educational purposes. The aims of this review are to: provide an overview of the AQG community and its activities, summarise the current trends and advances in AQG, highlight the changes that the area has undergone in the recent years, and suggest areas for improvement and future opportunities for AQG. Similar to what was found previously, there is little focus in the current literature on generating questions of controlled difficulty, enriching question forms and structures, automating template construction, improving presentation, and generating feedback. Our findings also suggest the need to further improve experimental reporting, harmonise evaluation metrics, and investigate other evaluation methods that are more feasible.

show abstract

Section: Verbalisationmentioning

confidence: 99%

A Systematic Review of Automatic Question Generation for Educational Purposes

Kurdi

Leo

Parsia

et al. 2019

Int J Artif Intell Educ

267

111

View full text Add to dashboard Cite

show abstract

“…CALL technology extended with Natural Language Processing (NLP) techniques became a new research and application field called Intelligent Computer-Assisted Language Learning (ICALL). Language technology has been integrated into CALL applications for the purposes of automated exercise generation (Ai et al 2015), complex error analysis and automated feedback generation (Amaral 2011). Petersen (2010) dinstiguishes Communicative ICALL and Non-Communicative ICALL.…”

Section: Intelligent Computer-assisted Language Learning (Icall)mentioning

confidence: 99%

The Dawn of the Human-Machine Era: A forecast of new and emerging language technologies

Sayers¹,

Sousa‐Silva²,

Höhn³

et al. 2021

View full text Add to dashboard Cite

New language technologies are coming, thanks to the huge and competing private investment fuelling rapid progress; we can either understand and foresee their effects, or be taken by surprise and spend our time trying to catch up. This report scketches out some transformative new technologies that are likely to fundamentally change our use of language. Some of these may feel unrealistically futuristic or far-fetched, but a central purpose of this report - and the wider LITHME network - is to illustrate that these are mostly just the logical development and maturation of technologies currently in prototype. But will everyone benefit from all these shiny new gadgets? Throughout this report we emphasise a range of groups who will be disadvantaged and issues of inequality. Important issues of security and privacy will accompany new language technologies. A further caution is to re-emphasise the current limitations of AI. Looking ahead, we see many intriguing opportunities and new capabilities, but a range of other uncertainties and inequalities. New devices will enable new ways to talk, to translate, to remember, and to learn. But advances in technology will reproduce existing inequalities among those who cannot afford these devices, among the world’s smaller languages, and especially for sign language. Debates over privacy and security will flare and crackle with every new immersive gadget. We will move together into this curious new world with a mix of excitement and apprehension - reacting, debating, sharing and disagreeing as we always do. Plug in, as the human-machine era dawns.

show abstract

“…While Automatic Question Generation (AQG) is not a new domain, studies conducted on this area largely diverse. A large proportion of existing works considers AQG as a solution to the continuous need for assessment questions in standardised tests, school and online courses as well as adaptive learning systems [10][11][12][13]. With the wave of neural networks, recent research also sees AQG as a method to improve the performance of Question Answering system by producing a large amount of labeled training data with less cost and human effort [14,15].…”

Section: Related Workmentioning

confidence: 99%

“…Most educational AQG systems focus on the generation of non-trivial factual fill-in-the-blank or multiple choice questions [11,12], while systems in other areas often aim to generate free response texts [14,15].…”

Section: Related Workmentioning

confidence: 99%

“…Both syntax and template based approaches rely on the input syntactic structure, with the syntax based approach generating questions by transforming the original structure [12,13], while the template based approach builds questions by completing some pre-designed templates with components from the input [15]. On the other hand, question construction in the semantic approach is solely based on the input underlying semantic structure, which is usually represented by some object languages [11,16]. Among all the aforementioned various categories, syntax based free response factual question generation is the best match for our interest, as the questions produced by this type of system allow educators to clearly illustrate the patterns in question formation and selection of interrogative pronouns to elementary level language learners.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Design and development of a question generator for learners of English

Blake

2021

SHS Web Conf.

View full text Add to dashboard Cite

In this paper, we describe the design and development of the first release of an online question generator. This pedagogic tool enables learners of English to generate open-ended, closed-ended and tag questions for a target sentence. Learners input a sentence (i.e. declarative statement) and select the type or types of questions to generate. Question generation is a non-trivial task involving numerous processes including syntactic transformation and pronoun selection. Syntactic transformation was achieved through the use of rules based on parse trees while the selection of interrogative pronouns was achieved using matching potential question foci with a linguistic knowledge encoded condition set. Lessons learned are detailed to help other researchers avoid or attempt to ameliorate the pitfalls and problems encountered in this study.

show abstract

Semi-automatic Generation of Multiple-Choice Tests from Mentions of Semantic Relations

Cited by 6 publications

References 7 publications

A Systematic Review of Automatic Question Generation for Educational Purposes

A Systematic Review of Automatic Question Generation for Educational Purposes

The Dawn of the Human-Machine Era: A forecast of new and emerging language technologies

Design and development of a question generator for learners of English

Contact Info

Product

Resources

About