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/GPT-2-Large (fine-tuning)

GPT-2-Large (fine-tuning)

Reported on 40 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Adversarial20 results

Text GenerationonDART
TER· 2021-07-14
0.46
SOTA
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (All)
TER· 2021-07-14
0.42
SOTA
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (Unseen)
TER· 2021-07-14
0.53
SOTA
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (Seen)
BLEU· 2021-07-14
65.3
best: 65.4 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (Seen)
METEOR· 2021-07-14
0.46
best: 45.85 (T5_large)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (Seen)
TER· 2021-07-14
0.33
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonDART
BERT· 2021-07-14
0.94
best: 0.9505 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonDART
BLEU· 2021-07-14
47
best: 48.74 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonDART
BLEURT· 2021-07-14
0.4
best: 0.6749 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonDART
METEOR· 2021-07-14
0.39
best: 40.74 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonDART
Mover· 2021-07-14
0.51
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (All)
BLEU· 2021-07-14
55.5
best: 59.7 (T5_large)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (All)
METEOR· 2021-07-14
0.42
best: 44.18 (T5_large)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (Unseen)
BLEU· 2021-07-14
43.1
best: 53.67 (T5_large)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonWebNLG (Unseen)
METEOR· 2021-07-14
0.38
best: 42.26 (T5_large)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonE2E
BLEU· 2021-07-14
68.5
best: 70.3 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonE2E
CIDEr· 2021-07-14
2.45
best: 2.47 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonE2E
METEOR· 2021-07-14
46
best: 46.3 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonE2E
NIST· 2021-07-14
8.78
best: 8.9 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Text GenerationonE2E
ROUGE-L· 2021-07-14
69.9
best: 70.8 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955

Natural Language Processing20 results

Table-to-Text GenerationonDART
TER· 2021-07-14
0.46
SOTA
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (All)
TER· 2021-07-14
0.42
SOTA
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (Unseen)
TER· 2021-07-14
0.53
SOTA
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (Seen)
BLEU· 2021-07-14
65.3
best: 65.4 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (Seen)
METEOR· 2021-07-14
0.46
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (Seen)
TER· 2021-07-14
0.33
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonDART
BERT· 2021-07-14
0.94
best: 0.9505 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonDART
BLEU· 2021-07-14
47
best: 48.47 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonDART
BLEURT· 2021-07-14
0.4
best: 0.6749 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonDART
METEOR· 2021-07-14
0.39
best: 0.4074 (T5B Baseline)
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonDART
Mover· 2021-07-14
0.51
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (All)
BLEU· 2021-07-14
55.5
best: 55.6 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (All)
METEOR· 2021-07-14
0.42
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (Unseen)
BLEU· 2021-07-14
43.1
best: 48.4 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonWebNLG (Unseen)
METEOR· 2021-07-14
0.38
best: 0.39 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonE2E
BLEU· 2021-07-14
68.5
best: 70.3 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonE2E
CIDEr· 2021-07-14
2.45
best: 2.47 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonE2E
METEOR· 2021-07-14
46
best: 46.3 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonE2E
NIST· 2021-07-14
8.78
best: 8.9 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955
Table-to-Text GenerationonE2E
ROUGE-L· 2021-07-14
69.9
best: 70.8 (HTLM (fine-tuning))
HTLM: Hyper-Text Pre-Training and Prompting of Language Models arXiv:2107.06955