ML Research Wiki / Benchmarks / Open-Domain Question Answering / ELI5

ELI5

Open-Domain Question Answering Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: Rouge-L

Top Performing Models

Rank Model Paper Rouge-L Date Code
1 Fourier Transformer Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator 26.90 2023-05-24 📦 lumia-group/fouriertransformer
2 QG Closed-book Question Generation via Contrastive Learning 26.40 2022-10-13 📦 dongxiangjue/closed-book-question-generation-via-contrastive-learning
3 BART BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension 24.30 2019-10-29 📦 huggingface/transformers 📦 nlmatics/llmsherpa 📦 facebookresearch/GENRE
4 E-MCA Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs 24.00 2019-10-18 📦 denisewong1/ASX300
5 Transformer Multitask + LayerDrop Reducing Transformer Depth on Demand with Structured Dropout 23.40 2019-09-25 📦 pytorch/fairseq 📦 prajjwal1/fluence 📦 prajjwal1/adaptive_transformer 📦 thunlp-mt/promptgating4mctg 📦 c00k1ez/plain-transformers
6 Multi-Inrerleave Improving Conditioning in Context-Aware Sequence to Sequence Models 14.63 2019-11-21 -

All Papers (6)

lumia-group/fouriertransformer
dongxiangjue/closed-book-question-generation-via-contrastive-learning
huggingface/transformers nlmatics/llmsherpa
denisewong1/ASX300
pytorch/fairseq prajjwal1/fluence