Model card
BART-base (STSM).
Metaunknown139M paramsTransformer
BART-base baseline from STSM paper (Self-training from Self-memory, arxiv:2401.10567, Jan 2024).
§ 01 · Benchmarks
Every benchmark BART-base (STSM) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | e2e | Computer Vision · Optical Character Recognition | bleu | 65.7% | #8 | 2024-01-19 | source ↗ |
| 02 | e2e | Computer Vision · Optical Character Recognition | cider | 2.2% | #8 | 2024-01-19 | source ↗ |
| 03 | e2e | Computer Vision · Optical Character Recognition | meteor | 45.6% | #8 | 2024-01-19 | source ↗ |
| 04 | e2e | Computer Vision · Optical Character Recognition | rouge-l | 68.8% | #8 | 2024-01-19 | source ↗ |
| 05 | e2e | Computer Vision · Optical Character Recognition | nist | 8.5% | #9 | 2024-01-19 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where BART-base (STSM) actually performs.
§ 03 · Papers
1 paper with results for BART-base (STSM).
- 2024-01-19· 5 results
Self-training from Self-memory in Data-to-text Generation
Hoang-Thang Ta, Abu Bakar Siddiqur Rahman, Akira Utsumi
§ 04 · Related models
Other Meta models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
papers-with-code
5
results
5 of 5 rows marked verified.