Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/ASA + RoBERTa

ASA + RoBERTa

Reported on 8 benchmarks across 7 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing8 results

Reading ComprehensiononDREAM
Accuracy· 2022-06-25
69.2
SOTA
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Visual Question Answering (VQA)onDREAM
Accuracy· 2022-06-25
69.2
SOTA
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Natural Language InferenceonMultiNLI
Matched· 2022-06-25
88
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Semantic Textual SimilarityonSTS Benchmark
Spearman Correlation· 2022-06-25
0.892
best: 0.931 (Mnet-Sim)
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Semantic Textual SimilarityonQuora Question Pairs
F1· 2022-06-25
73.7
best: 90.7 (ALICE)
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2022-06-25
96.3
best: 97.5 (T5-11B)
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Named Entity Recognition (NER)onWNUT 2017
F1· 2022-06-25
57.3
best: 60.45 (CL-KL)
Adversarial Self-Attention for Language Understanding arXiv:2206.12608
Paraphrase IdentificationonQuora Question Pairs
F1· 2022-06-25
73.7
best: 90.7 (ALICE)
Adversarial Self-Attention for Language Understanding arXiv:2206.12608