• Corpus ID: 2387668

Automatic factual question generation from text

@inproceedings{Smith2011AutomaticFQ,
  title={Automatic factual question generation from text},
  author={Noah A. Smith and Michael Heilman},
  year={2011}
}
Texts with potential educational value are becoming available through the Internet (e.g., Wikipedia, news services. [] Key Method The questions could then be presented to a teacher, who could select and revise the ones that he or she judges to be useful. After introducing the problem, we describe some of the computational and linguistic challenges presented by factual question generation. We then present an implemented system that leverages existing natural language processing techniques to address some of…
cs.cmu.edu
172 Citations
Highly Influential Citations
19
Background Citations
89
Methods Citations
53
Results Citations
2

172 Citations

Citation Type

Citation Type

Questions Generation for Reading Comprehension using Coherence Relations
TLDR
A system that takes a reading comprehension text as input and outputs all questions for the selected domain, that follows the input domain, and shows the effectiveness of the approach with previous Heilman and Smith MH method.
Factual Question Generation for the Portuguese Language
TLDR
This work presents a tool for generating factual questions in Portuguese by proposing three distinct approaches that carry out a semantic analysis of the sentences, through Semantic Role Labeling (SRL), and extracts the inherent dependencies within sentences using Dependency Parsing.
Factual open cloze question generation for assessment of learner’s knowledge
TLDR
An automatic factual open cloze question generation system which can generate fill-in-the-blank questions without alternatives and suggested answer hints for the examinees to reduce the number of possible answers that make assessment easier.
Question Generation for Language Learning: From ensuring texts are read to supporting learning
TLDR
This paper discusses two types of questions serving this purpose, how they can be generated automatically; and reports on a crowd-sourcing evaluation comparing automatically generated to manually written questions targeting particle verbs, a challenging linguistic form for learners of English.
Linguistic Appropriateness and Pedagogic Usefulness of Reading Comprehension Questions
TLDR
Results show that manually generated questions are in general both of higher linguistic as well as pedagogic quality and that among the human generated questions, teacher-generated ones tend to be most useful.
Infusing Automatic Question Generation with Natural Language Understanding
TLDR
The automatic question generation system accompanying this dissertation is MARGE, which is a recursive acronym for: MARGE automatically reads generates and evaluates, and is the first question Generation system to successfully generate meaningful questions from textual units larger than a sentence.
Focused Questions and Answer Generation by Key Content Selection
TLDR
This paper proposes a method of automatically generating answers and diversified sequences corresponding to those answers by introducing a new module called the "Focus Generator", which guides the decoder in an existing "encoder-decoder" model to generate questions based on selected focus contents.
Automatic Question Generation in Multimedia-Based Learning
TLDR
The results indicate that the presence of pre-questions improves the performance of test-takers and that the psychometric parameters of the questions generated by the authors’ system are comparable if not better than those of the state-of-the-art system.
Crowdsourcing evaluation of the quality of automatically generated questions for supporting computer-assisted language teaching
TLDR
This work combines insights from research in second language acquisition and computational linguistics to automatically generate text-based questions to a given text that draw the learner’s attention to target linguistic forms by requiring them to use the forms or their paraphrases in the answer.
Thematic Question Generation over Knowledge Bases
TLDR
This paper developed a template based approach to generate questions, allowing complex questions generation from binary and n-ary statements, and developed an approach that reverts templates used for questions answering, allowing us to import more than 2000 templates.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 211 REFERENCES
Automated Question Generation Methods for Intelligent English Learning Systems and its Evaluation
This paper presents methods of automated generation of questions about the contents of an English story. The methods are used for realizing adaptive Question and Answer functions which give suitable…
Automatic Question Generation for Literature Review Writing Support
TLDR
It is found that the human evaluators have moderate difficulties distinguishing questions generated by the proposed system from those produced by human (F-score=0.43), and further results show that the system significantly outscores Generic Question on overall quality measures.
Generating Instruction Automatically for the Reading Strategy of Self-Questioning
TLDR
This paper describes how to generate self-questioning instruction for an automated reading tutor and decomposes strategy instruction into describing, modeling, scaffolding, and prompting the strategy.
Automatic Question Generation for Vocabulary Assessment
TLDR
Experimental results suggest that these automatically-generated questions give a measure of vocabulary skill that correlates well with subject performance on independently developed human-written questions and strong correlations with standardized vocabulary tests point to the validity of this approach to automatic assessment of word knowledge.
Question Generation with Minimal Recursion Semantics
TLDR
The performance of proposed method is compared against other syntax and rule based systems, and the result reveals the challenges of current research on question generation and indicates direction for future work.
Computer-aided generation of multiple-choice tests
  • R. Mitkov, Le An Ha
  • Computer Science
    International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003
  • 2003
TLDR
The results from the conducted evaluation suggest that the new procedure is very effective saving time and labour considerably and that the test items produced with the help of the program are not of inferior quality to those produced manually.
Diagnosing Meaning Errors in Short Answers to Reading Comprehension Questions
TLDR
A Content-Assessment Module (CAM) is developed, which performs shallow semantic analysis to diagnose meaning errors and reaches an accuracy of 88% for semantic error detection and 87% on semantic error diagnosis on a held-out test data set.
Good Question! Statistical Ranking for Question Generation
TLDR
This work uses manually written rules to perform a sequence of general purpose syntactic transformations to turn declarative sentences into questions, which are ranked by a logistic regression model trained on a small, tailored dataset consisting of labeled output from the system.
Automated Grammatical Error Correction for Language Learners
TLDR
The motivation for the COLING tutorial is to make others more aware of this field and its particular set of challenges, and to engage researchers from other NLP fields to develop novel and effective approaches to these problems.
Extracting Simplified Statements for Factual Question Generation
TLDR
Experimental results indicate that the proposed algorithm for extracting simplified sentences from appositives, subordinate clauses, and other constructions is more suitable for factual question generation applications than an alternative text compression algorithm.
...
1
2
3
4
5
...