Multiple Choice Question Generation Utilizing An Ontology

Stasaski, Katherine; Hearst, Marti A.

doi:10.18653/v1/w17-5034

Cited by 55 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In work [4], the question generation is made on the ontological structure, for example, the phylogenetic tree of species, presented as a graph, where the vertices are the categories titles and the connections are the relations between categories. Using the "expanding" of the categories titles and their relationships with the manually written rules for question generation, authors received the questions that allow them to check structural knowledge of the topic.…”

Section: The Review Of Recent Approaches To the Question Generation From The Textmentioning

confidence: 99%

Metagraph Based Approach for Neural Text Question Generation

Belyanova

Chernobrovkin

Latkin

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The paper considers the task of generating questions by given text. The generation of high-quality questions allows us to solve many problems, for example, in the field of teaching -for the automatic creation of tests for training materials or the enrichment of interaction techniques for question-answering systems. Leading research in this area shows that models based on the Seq2Seq architecture achieve the best quality. However, such models do not use the hidden structure of the text, which is essential for generating semantically correct questions. New works on this topic use additional data in the form of the graphs, representing the dependencies of the words in a sentence. In this article, an approach that uses a metagraph model of text as the initial structure for storing and enriching data with additional information and semantic relationships is considered. After generating a metagraph model of the text, the metagraph is decomposed into a multipartite graph, which allows its usage in existing models for generating text questions without losing information about the additional hierarchical and semantical dependencies of the text.

show abstract

Section: The Review Of Recent Approaches To the Question Generation From The Textmentioning

confidence: 99%

Metagraph Based Approach for Neural Text Question Generation

Belyanova

Chernobrovkin

Latkin

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…D. There have been thousands of fans attending the festival. Existing works conduct some attempts on generating short distractors (Stasaski and Hearst, 2017;Guo et al, 2016). These approaches formulate distractor generation as a similar word selection task.…”

Section: Questionmentioning

confidence: 99%

“…Some works (Stasaski and Hearst, 2017;Guo et al, 2016;Kumar et al, 2015;Afzal and Mitkov, 2014) focused on finding answer-relevant ontologies or words as the distractors with the help of WordNet and Word2Vec. For example, Stasaski and Hearst (2017) leveraged an educational Biology ontology to conduct the distractor generation. However, some of these works depend heavily on the well-designed ontology and they can only generate short distractors, which usually only contain one single word or phrase.…”

Section: Related Workmentioning

confidence: 99%

Automatic Distractor Generation for Multiple Choice Questions in Standard Tests

Qiu¹,

Wang²,

Wang³

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

To assess the knowledge proficiency of a learner, multiple choice question is an efficient and widespread form in standard tests. However, the composition of the multiple choice question, especially the construction of distractors is quite challenging. The distractors are required to both incorrect and plausible enough to confuse the learners who did not master the knowledge. Currently, the distractors are generated by domain experts which are both expensive and timeconsuming. This urges the emergence of automatic distractor generation, which can benefit various standard tests in a wide range of domains. In this paper, we propose a quEstion and answer guided Distractor GEneration (EDGE) framework to automate distractor generation. EDGE consists of three major modules: (1) the Reforming Question Module and the Reforming Passage Module apply gate layers to guarantee the inherent incorrectness of the generated distractors; (2) the Distractor Generator Module applies attention mechanism to control the level of plausibility. Experimental results on a large-scale public dataset demonstrate that our model significantly outperforms existing models and achieves a new state-of-the-art.

show abstract

“…Existing approaches to distractor selection use WordNet (Fellbaum, 1998) metrics (Mitkov and Ha, 2003;Chen et al, 2015), word embedding similarities (Jiang and Lee, 2017), thesauruses (Sumita et al, 2005;Smith et al, 2010), and phonetic and morphological similarities (Pino and Eskenazi, 2009). Other approaches consider grammatical correctness, and introduce structural similarities in an ontology (Stasaski and Hearst, 2017), and syntactic similarities (Chen et al, 2006). When using broader context, bigram or n-gram co-occurrence (Susanti et al, 2018;Hill and Simha, 2016), context similarity (Pino et al, 2008), and context sensitive inference (Zesch and Melamud, 2014) have also been applied to distractor selection.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications

2020

View full text Add to dashboard Cite

Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models. More recent methods have improved performance by discarding these features and utilizing deep learning models. However, it is unknown whether augmenting deep learning models with linguistically motivated features would improve performance further. This paper combines these two approaches with the goal of improving overall model performance and addressing this question. Evaluating on two large readability corpora, we find that, given sufficient training data, augmenting deep learning models with linguistically motivated features does not improve state-of-the-art performance. Our results provide preliminary evidence for the hypothesis that the state-of-theart deep learning models represent linguistic features of the text related to readability. Future research on the nature of representations formed in these models can shed light on the learned features and their relations to linguistically motivated ones hypothesized in traditional approaches.

show abstract

Multiple Choice Question Generation Utilizing An Ontology

Cited by 55 publications

References 13 publications

Metagraph Based Approach for Neural Text Question Generation

Metagraph Based Approach for Neural Text Question Generation

Automatic Distractor Generation for Multiple Choice Questions in Standard Tests

Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications

Contact Info

Product

Resources

About