Question Generation

The goal of Question Generation is to generate a valid and fluent question according to a given passage and the target answer. Question Generation can be used in many scenarios, such as automatic tutoring systems, improving the performance of Question Answering models and enabling chatbots to lead a conversation.

Source: Generating Highly Relevant Questions

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 301–325 of 664 papers

Title	Date	Tasks	Status	Hype
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages	Mar 10, 2022	ArticlesBenchmarking	—Unverified	0
On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation	Mar 9, 2022	Question GenerationQuestion-Generation	CodeCode Available	0
IT5: Text-to-text Pretraining for Italian Language Understanding and Generation	Mar 7, 2022	DecoderHeadline Generation	CodeCode Available	1
QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation	Feb 14, 2022	Multi-hop Question AnsweringQuestion Answering	CodeCode Available	1
Question Generation for Evaluating Cross-Dataset Shifts in Multi-modal Grounding	Jan 24, 2022	Question AnsweringQuestion Generation	—Unverified	0
Unified Question Generation with Continual Lifelong Learning	Jan 24, 2022	Lifelong learningQuestion Answering	—Unverified	0
Leaf: Multiple-Choice Question Generation	Jan 22, 2022	Multiple-choiceQuestion Answering	CodeCode Available	1
Improving Biomedical Information Retrieval with Neural Retrievers	Jan 19, 2022	Biomedical Information RetrievalInformation Retrieval	—Unverified	0
Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Graph	Jan 16, 2022	DecoderMeta-Learning	—Unverified	0
JEFF - Just Another EFFicient Reading Comprehension Test Generation	Jan 16, 2022	Question GenerationQuestion-Generation	—Unverified	0
Consecutive Question Generation with Multitask Joint Reranking and Dynamic Rationale Search	Jan 16, 2022	DiversityInformativeness	—Unverified	0
All You May Need for VQA are Image Captions	Jan 16, 2022	AllImage Captioning	—Unverified	0
QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization	Jan 16, 2022	Question AnsweringQuestion Generation	—Unverified	0
TRUE: Re-evaluating Factual Consistency Evaluation	Jan 16, 2022	Question GenerationQuestion-Generation	—Unverified	0
Data Augmentation for Biomedical Factoid Question Answering	Jan 16, 2022	Data AugmentationInformation Retrieval	—Unverified	0
MixQG: Neural Question Generation with Mixed Answer Types	Jan 16, 2022	Multiple-choiceQuestion Answering	—Unverified	0
Cooperative Self-training of Machine Reading Comprehension	Jan 16, 2022	Extractive Question-AnsweringMachine Reading Comprehension	—Unverified	0
V-Doc: Visual Questions Answers With Documents	Jan 1, 2022	Question AnsweringQuestion Generation	—Unverified	0
An ASP-based Approach to Answering Natural Language Questions for Texts	Dec 21, 2021	Question AnsweringQuestion Generation	—Unverified	0
Self-supervised clarification question generation for ambiguous multi-turn conversation	Dec 17, 2021	Conversational RecommendationQuestion Generation	—Unverified	0
QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization	Dec 16, 2021	Question AnsweringQuestion Generation	CodeCode Available	1
ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs	Dec 13, 2021	Information RetrievalKnowledge Graphs	—Unverified	0
Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices	Dec 7, 2021	Natural Language UnderstandingQuestion Answering	—Unverified	0
Improving Controllability of Educational Question Generation by Keyword Provision	Dec 2, 2021	DiversityQuestion Generation	—Unverified	0
Temporal Question Generation from History Text	Dec 1, 2021	Question GenerationQuestion-Generation	—Unverified	0

Show:10 25 50

← PrevPage 13 of 27Next →

All datasets SQuAD1.1 COCO Visual Question Answering (VQA) real images 1.0 open ended GrailQA-Compositional GrailQA-IID GrailQA-Zero-Shot FairytaleQA WeiboPolls Natural Questions SQuAD TriviaQA Visual Question Generation

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ERNIE-GENLARGE (beam size=5)	BLEU-4	25.41	—	Unverified
2	BART (TextBox 2.0)	BLEU-4	25.08	—	Unverified
3	ProphetNet + ASGen	BLEU-4	24.44	—	Unverified
4	UniLMv2	BLEU-4	24.43	—	Unverified
5	ProphetNet + syn. mask + localness	BLEU-4	24.37	—	Unverified
6	ProphetNet	BLEU-4	23.91	—	Unverified
7	UniLM + ASGen	BLEU-4	23.7	—	Unverified
8	UniLM	BLEU-4	22.78	—	Unverified
9	BERTSQG	BLEU-4	22.17	—	Unverified
10	Selector & NQG++	BLEU-4	15.87	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MDN	BLEU-1	65.1	—	Unverified
2	coco-Caption [[Karpathy and Li2014]]	BLEU-1	62.5	—	Unverified
3	Max(Yang,2015)	BLEU-1	59.4	—	Unverified
4	Sample(Yang,2015)	BLEU-1	38.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FactJointGT	METEOR	36.21	—	Unverified
2	JointGT	METEOR	36.08	—	Unverified
3	FactT5B	METEOR	35.72	—	Unverified
4	T5B	METEOR	35.64	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FactT5B	BLEU	46.1	—	Unverified
2	JointGT	BLEU	45.95	—	Unverified
3	T5B	BLEU	44.51	—	Unverified
4	FactJointGT	BLEU	43.61	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	JointGT	METEOR	37.69	—	Unverified
2	FactJointGT	METEOR	37.55	—	Unverified
3	FactT5B	METEOR	37.39	—	Unverified
4	T5B	METEOR	37.35	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART fine-tuned on FairytaleQA	ROUGE-L	0.53	—	Unverified
2	BART fine-tuned on NarrativeQA and FairytaleQA	ROUGE-L	0.52	—	Unverified
3	BART fine-tuned on NarrativeQA	ROUGE-L	0.44	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UniPoll	ROUGE-1	49.6	—	Unverified
2	T5	ROUGE-1	44.46	—	Unverified
3	Dual Dec	ROUGE-1	38.24	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Info-HCVAE	QAE	37.18	—	Unverified
2	HCVAE	QAE	31.45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Info-HCVAE	QAE	71.18	—	Unverified
2	HCVAE	QAE	69.46	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Info-HCVAE	QAE	35.45	—	Unverified
2	HCVAE	QAE	30.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MDN	BLEU-1	36	—	Unverified