SOTAVerified

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

Showing 91–100 of 664 papers

TitleStatusHype
EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RLCode1
EduQG: A Multi-format Multiple Choice Dataset for the Educational DomainCode1
Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric SummarizationCode1
Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question GenerationCode1
Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention NetworksCode1
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage RetrievalCode1
BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale PretrainingCode1
Bench4KE: Benchmarking Automated Competency Question GenerationCode1
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-trainingCode1
HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World ClaimsCode1
Show:102550
← PrevPage 10 of 67Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ERNIE-GENLARGE (beam size=5)BLEU-425.41—Unverified
2BART (TextBox 2.0)BLEU-425.08—Unverified
3ProphetNet + ASGenBLEU-424.44—Unverified
4UniLMv2BLEU-424.43—Unverified
5ProphetNet + syn. mask + localnessBLEU-424.37—Unverified
6ProphetNetBLEU-423.91—Unverified
7UniLM + ASGenBLEU-423.7—Unverified
8UniLMBLEU-422.78—Unverified
9BERTSQGBLEU-422.17—Unverified
10Selector & NQG++BLEU-415.87—Unverified
#ModelMetricClaimedVerifiedStatus
1MDNBLEU-165.1—Unverified
2coco-Caption [[Karpathy and Li2014]]BLEU-162.5—Unverified
3Max(Yang,2015)BLEU-159.4—Unverified
4Sample(Yang,2015)BLEU-138.8—Unverified
#ModelMetricClaimedVerifiedStatus
1FactJointGTMETEOR36.21—Unverified
2JointGTMETEOR36.08—Unverified
3FactT5BMETEOR35.72—Unverified
4T5BMETEOR35.64—Unverified
#ModelMetricClaimedVerifiedStatus
1FactT5BBLEU46.1—Unverified
2JointGTBLEU45.95—Unverified
3T5BBLEU44.51—Unverified
4FactJointGTBLEU43.61—Unverified
#ModelMetricClaimedVerifiedStatus
1JointGTMETEOR37.69—Unverified
2FactJointGTMETEOR37.55—Unverified
3FactT5BMETEOR37.39—Unverified
4T5BMETEOR37.35—Unverified
#ModelMetricClaimedVerifiedStatus
1BART fine-tuned on FairytaleQAROUGE-L0.53—Unverified
2BART fine-tuned on NarrativeQA and FairytaleQAROUGE-L0.52—Unverified
3BART fine-tuned on NarrativeQAROUGE-L0.44—Unverified
#ModelMetricClaimedVerifiedStatus
1UniPollROUGE-149.6—Unverified
2T5ROUGE-144.46—Unverified
3Dual DecROUGE-138.24—Unverified
#ModelMetricClaimedVerifiedStatus
1Info-HCVAEQAE37.18—Unverified
2HCVAEQAE31.45—Unverified
#ModelMetricClaimedVerifiedStatus
1Info-HCVAEQAE71.18—Unverified
2HCVAEQAE69.46—Unverified
#ModelMetricClaimedVerifiedStatus
1Info-HCVAEQAE35.45—Unverified
2HCVAEQAE30.2—Unverified
#ModelMetricClaimedVerifiedStatus
1MDNBLEU-136—Unverified