TrICy (trK = trk* = 0.24)

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

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

Adversarial3 results

Text GenerationonWebNLG
Number of parameters (M)· 2024-01-25
6.2
SOTA
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy arXiv:2402.01714
Text GenerationonWebNLG
BLEU· 2024-01-25
64.73
best: 67.32 (Control Prefixes (A1, T5-large))
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy arXiv:2402.01714
Text GenerationonWebNLG
METEOR· 2024-01-25
45.53
best: 48.35 (T5B Baseline)
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy arXiv:2402.01714

Natural Language Processing3 results

Data-to-Text GenerationonWebNLG
Number of parameters (M)· 2024-01-25
6.2
SOTA
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy arXiv:2402.01714
Data-to-Text GenerationonWebNLG
BLEU· 2024-01-25
64.73
best: 67.32 (Control Prefixes (A1, T5-large))
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy arXiv:2402.01714
Data-to-Text GenerationonWebNLG
METEOR· 2024-01-25
45.53
best: 48.35 (T5B Baseline)
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy arXiv:2402.01714