Optical Character Recognition2020en

mldoc-zero-shot-english-to-german

Dataset from Papers With Code

Metrics:accuracy, cer, wer, f1
Current State of the Art

XLMft UDA

Unknown

96.95

accuracy

accuracy Progress Over Time

Showing 3 breakthroughs from May 2018 to Sep 2019

79.684.389.193.898.5May 2018Dec 2018Sep 2019accuracyDate

Key Milestones

May 2018
MultiCCA + CNN

From paper: A Corpus for Multilingual Document Classification in Eight Languages

81.2
Dec 2018
Massively Multilingual Sentence Embeddings

From paper: Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

84.8
+4.4%
Sep 2019
XLMft UDACurrent SOTA

From paper: Bridging the domain gap in cross-lingual document classification

97.0
+14.4%
Total Improvement
19.4%
Time Span
1y 4m
Breakthroughs
3
Current SOTA
97.0

Top Models Performance Comparison

Top 5 models ranked by accuracy

accuracy1XLMft UDA97.0100.0%2MultiFiT, pseudo91.694.5%3Massively Multilingual Se...84.887.4%4MultiCCA + CNN81.283.8%5BiLSTM (Europarl)71.874.1%0%25%50%75%100%% of best
Best Score
97.0
Top Model
XLMft UDA
Models Compared
5
Score Range
25.1

accuracyPrimary

Related Papers4

Other Optical Character Recognition Datasets