TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Question Generation/SQuAD1.1

Question Generation on SQuAD1.1

Metric: BLEU-4 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕BLEU-4▼Extra DataPaperDate↕Code
1ERNIE-GENLARGE (beam size=5)25.41YesERNIE-GEN: An Enhanced Multi-Flow Pre-training a...2020-01-26Code
2BART (TextBox 2.0)25.08NoTextBox 2.0: A Text Generation Library with Pre-...2022-12-26Code
3ProphetNet + ASGen24.44Yes---
4UniLMv224.43YesUniLMv2: Pseudo-Masked Language Models for Unifi...2020-02-28Code
5ProphetNet + syn. mask + localness24.37NoEnhancing Pre-trained Models with Text Structure...2022-09-09-
6ProphetNet23.91YesProphetNet: Predicting Future N-gram for Sequenc...2020-01-13Code
7UniLM + ASGen23.7Yes---
8UniLM22.78YesUnified Language Model Pre-training for Natural ...2019-05-08Code
9BERTSQG22.17Yes--Code
10Selector & NQG++15.874NoMixture Content Selection for Diverse Sequence G...2019-09-04Code
11MPQG13.91No--Code
12RNN +attn +copy13.5NoEvaluating Rewards for Question Generation Models2019-02-28Code
13NQG++13.27NoNeural Question Generation from Text: A Prelimin...2017-04-06Code