Optical Character Recognition2020en
mldoc-zero-shot-english-to-chinese
Dataset from Papers With Code
Metrics:accuracy, cer, wer, f1
Current State of the Art
XLMft UDA
Unknown
93.32
accuracy
accuracy Progress Over Time
Showing 2 breakthroughs from May 2018 to Sep 2019
Key Milestones
Total Improvement
24.9%
Time Span
1y 4m
Breakthroughs
2
Current SOTA
93.3
Top Models Performance Comparison
Top 5 models ranked by accuracy
Best Score
93.3
Top Model
XLMft UDA
Models Compared
5
Score Range
21.4
accuracyPrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | XLMft UDA | 93.32 | Sep 2019 | |
| 2 | MultiFiT, pseudo | 82.48 | Sep 2019 | |
| 3 | MultiCCA + CNN | 74.73 | May 2018 | |
| 4 | BiLSTM (UN) | 71.97 | May 2018 | |
| 5 | Massively Multilingual Sentence Embeddings | 71.93 | Dec 2018 |
Related Papers4
Bridging the domain gap in cross-lingual document classification
Sep 2019Models: XLMft UDA
MultiFiT: Efficient Multi-lingual Language Model Fine-tuning
Sep 2019Models: MultiFiT, pseudo
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
Dec 2018Models: Massively Multilingual Sentence Embeddings
A Corpus for Multilingual Document Classification in Eight Languages
May 2018Models: MultiCCA + CNN, BiLSTM (UN)