self-mem + new data (random)

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

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

Natural Language Processing1 result

Data-to-Text GenerationonE2E
METEOR· 2024-01-19
46.11
SOTA
Self-training from Self-memory in Data-to-text Generation arXiv:2401.10567

Adversarial1 result

Text GenerationonE2E
METEOR· 2024-01-19
46.11
best: 46.3 (HTLM (fine-tuning))
Self-training from Self-memory in Data-to-text Generation arXiv:2401.10567