Codesota · Computer Vision · Optical Character Recognition · wikibioTasks/Computer Vision/Optical Character Recognition
Optical Character Recognition · benchmark dataset · 2020 · EN

wikibio.

Dataset from Papers With Code

Saturated benchmark

Benchmark abandoned or no longer evaluated by the community

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

18 results indexed across 3 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary
accuracy · higher is better
All metrics
bleu, parent, rouge
bleu
9 rows
#ModelOrgSubmittedPaper / codebleu
01Accurate Content Copying—Nov 2021paper46.87
02SANA—May 2021paper45.78
03Bert-to-Bert—May 2021paper45.62
04FA+RL—Nov 2021paper45.47
05NCP+BTA—Nov 2021paper45.46
06Field-gating Seq2seq + dual attention—Nov 2017Table-to-text Generation by Structure-aware Seq2seq Lear… · code44.89
07Field-gating Seq2seq + dual attention + beam search—Nov 2017Table-to-text Generation by Structure-aware Seq2seq Lear… · code44.71
08MBD—Feb 2021Controlling Hallucinations at Word Level in Data-to-Text… · code41.56
09Table NLM—Mar 2016Neural Text Generation from Structured Data with Applica… · code34.70
parent
3 rows
#ModelOrgSubmittedPaper / codeparent
01MBD—Feb 2021Controlling Hallucinations at Word Level in Data-to-Text… · code56.16
02SANA—May 2021paper55.42
03Bert-to-Bert—May 2021paper53.54
rouge
6 rows
#ModelOrgSubmittedPaper / coderouge
01Accurate Content Copying—Nov 2021paper42.28
02Field-gating Seq2seq + dual attention + beam search—Nov 2017Table-to-text Generation by Structure-aware Seq2seq Lear… · code41.65
03FA+RL—Nov 2021paper41.54
04Field-gating Seq2seq + dual attention—Nov 2017Table-to-text Generation by Structure-aware Seq2seq Lear… · code41.21
05NCP+BTA—Nov 2021paper40.31
06Table NLM—Mar 2016Neural Text Generation from Structured Data with Applica… · code25.80
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 04 · Literature

3 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies