issues
search
alan-turing-institute
/
ARC-MTQE
Critical Error Detection for Machine Translation
MIT License
1
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Remove datasets
#103
radka-j
closed
4 months ago
0
Fix python version at <3.11
#102
radka-j
closed
4 months ago
0
Documentation update
#101
joannacknight
closed
4 months ago
0
Docs update
#100
radka-j
closed
5 months ago
1
Min max eval
#99
joannacknight
closed
5 months ago
1
Baseline evaluation
#98
radka-j
closed
5 months ago
0
[WIP] Updates to ReadMe
#97
joannacknight
closed
5 months ago
1
Analysis
#96
joannacknight
closed
5 months ago
2
Check and update READMEs
#95
radka-j
closed
5 months ago
0
Number of segments per language pair in training data for multilingual all
#94
radka-j
closed
5 months ago
1
Use William's significance test to compare models
#93
radka-j
closed
5 months ago
0
Eval mean median
#92
joannacknight
closed
5 months ago
2
What does an MCC of 0.X mean?
#91
joannacknight
closed
5 months ago
3
Evaluation of LLM predictions
#90
joannacknight
closed
5 months ago
0
Evaluate MCC by annotator
#89
radka-j
closed
5 months ago
1
Evaluation on different thresholds
#88
joannacknight
closed
5 months ago
1
Prediction performance by annotator agreement
#87
radka-j
closed
5 months ago
0
Add baseline prediction logs
#86
radka-j
closed
5 months ago
1
[WIP] Predictions and evaluations
#85
joannacknight
closed
5 months ago
0
Evaluation for different thresholds
#84
joannacknight
closed
6 months ago
1
Add logging
#83
radka-j
closed
6 months ago
4
Second step en-de config files - wmt22
#82
joannacknight
closed
6 months ago
0
Create slurm scripts for predictions
#81
joannacknight
closed
6 months ago
1
Generate predictions slurm scripts
#80
joannacknight
closed
5 months ago
0
Add utility function to create latex table
#79
radka-j
closed
6 months ago
0
Add baseline predictions
#78
radka-j
closed
6 months ago
2
Finalise evaluation plan
#77
radka-j
closed
6 months ago
0
More experiments
#76
radka-j
closed
6 months ago
0
Double check GPT response content
#75
radka-j
closed
6 months ago
1
Write report
#74
radka-j
closed
5 months ago
1
Create model ensembles
#73
radka-j
closed
5 months ago
1
Run another one-step DEMETR experiment with smaller data-size
#72
radka-j
closed
6 months ago
1
Decide strategy for dealing with long sentences in WMT 2022 En-De data
#71
radka-j
closed
6 months ago
0
Evaluation of predictions
#70
joannacknight
closed
6 months ago
7
Add CSVs with GPT responses
#69
radka-j
closed
6 months ago
0
Base models config
#68
joannacknight
closed
6 months ago
1
Data updates and fixes
#67
radka-j
closed
6 months ago
0
Save GPT output to CSVs
#66
radka-j
closed
6 months ago
0
Evaluate predictions from the models
#65
joannacknight
closed
6 months ago
5
WMT21 style GPT prompt
#64
radka-j
closed
6 months ago
1
Add datasets for remaining experiments
#63
radka-j
closed
6 months ago
4
Save last checkpoint
#62
joannacknight
closed
6 months ago
1
GPT with WMT21 annotator guidelines prompt
#61
radka-j
closed
6 months ago
1
Produce test results for all models
#60
radka-j
closed
6 months ago
3
Use WMT21 CE definitions in GPT prompt
#59
radka-j
closed
6 months ago
0
Save intermediate datasets for two stage training
#58
radka-j
closed
6 months ago
0
German-English experiments with WMT22 synthetic data
#57
radka-j
closed
6 months ago
3
Train CED models with two step training
#56
radka-j
closed
6 months ago
7
Load checkpoint
#55
radka-j
closed
6 months ago
6
Add training configs
#54
radka-j
closed
6 months ago
1
Next