Question Generation On Squad11

Metrics

BLEU-4

METEOR

ROUGE-L

Results

Performance results of various models on this benchmark

				Paper Title
ERNIE-GENLARGE (beam size=5)	25.41	-	-	ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation
BART (TextBox 2.0)	25.08	26.73	52.55	TextBox 2.0: A Text Generation Library with Pre-trained Language Models
ProphetNet + ASGen	24.44	26.73	52.8	Learning to Generate Questions by Recovering Answer-containing Sentences
UniLMv2	24.43	-	-	UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
ProphetNet + syn. mask + localness	24.37	26.26	52.77	Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation
ProphetNet	23.91	26.6	52.3	ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
UniLM + ASGen	23.7	25.9	52.3	Learning to Generate Questions by Recovering Answer-containing Sentences
UniLM	22.78	25.1	51.1	Unified Language Model Pre-training for Natural Language Understanding and Generation
BERTSQG	22.17	-	-	A Recurrent BERT-based Model for Question Generation
Selector & NQG++	15.874	-	-	Mixture Content Selection for Diverse Sequence Generation
MPQG	13.91	-	-	Leveraging Context Information for Natural Question Generation
RNN +attn +copy	13.5	-	-	Evaluating Rewards for Question Generation Models
NQG++	13.27	-	-	Neural Question Generation from Text: A Preliminary Study

0 of 13 row(s) selected.

Question Generation On Squad11 | SOTA | HyperAI