Codesota · Computer Vision · Optical Character Recognition · mldoc-zero-shot-english-to-frenchTasks/Computer Vision/Optical Character Recognition
Optical Character Recognition · benchmark dataset · 2020 · EN

mldoc-zero-shot-english-to-french.

Dataset from Papers With Code

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

6 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
accuracy · higher is better
accuracy· primary
6 rows
#ModelOrgSubmittedPaper / codeaccuracy
01XLMft UDA—Sep 2019Bridging the domain gap in cross-lingual document classi… · code96.05
02MultiFiT, pseudo—Sep 2019MultiFiT: Efficient Multi-lingual Language Model Fine-tu… · code89.42
03Massively Multilingual Sentence Embeddings—Dec 2018Massively Multilingual Sentence Embeddings for Zero-Shot… · code77.95
04BiLSTM (UN)—May 2018A Corpus for Multilingual Document Classification in Eig… · code74.52
05BiLSTM (Europarl)—May 2018A Corpus for Multilingual Document Classification in Eig… · code72.83
06MultiCCA + CNN—May 2018A Corpus for Multilingual Document Classification in Eig… · code72.38
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.
§ 03 · Progress

4 steps
of state of the art.

Each row below marks a model that broke the previous record on accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · accuracy
  1. May 24, 2018BiLSTM (UN)74.52
  2. Dec 26, 2018Massively Multilingual Sentence Embeddings77.95
  3. Sep 10, 2019MultiFiT, pseudo89.42
  4. Sep 16, 2019XLMft UDA96.05
Fig 3 · SOTA-setting models only. 4 entries span May 2018 → Sep 2019.
§ 04 · Literature

4 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