self-mem + new data

Reported on 2 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.

Adversarial1 result

Text GenerationonDART
BLEU· 2024-01-19
47.76
best: 48.74 (T5B Baseline)
SOTA
Self-training from Self-memory in Data-to-text Generation arXiv:2401.10567

Natural Language Processing1 result

Data-to-Text GenerationonDART
BLEU· 2024-01-19
47.76
best: 48.47 (T5B Baseline)
SOTA
Self-training from Self-memory in Data-to-text Generation arXiv:2401.10567