issues
search
neulab
/
compare-mt
A tool for holistic analysis of language generations systems
BSD 3-Clause "New" or "Revised" License
466
stars
59
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fix bar chart color cycling
#134
Proyag
closed
2 years ago
1
feat: add lru cache to porter stemmer
#133
lyuyangh
closed
2 years ago
0
Fix sacrebleu and NLTK interfaces
#132
neubig
closed
2 years ago
0
[WIP] Added publication to pypi through actions
#131
neubig
closed
2 years ago
0
Unit tests are failing
#130
neubig
closed
2 years ago
1
Added CI through github actions
#129
neubig
closed
2 years ago
0
Fixed an issue with imports in setup.py
#128
neubig
closed
2 years ago
0
pip install errors
#127
pfliu-nlp
closed
2 years ago
6
Consider model variance in bootstrap resampling test
#126
odashi
opened
2 years ago
6
add multilabel bucketer
#125
kayoyin
closed
3 years ago
1
bootstrap sample size
#124
ozancaglayan
opened
3 years ago
0
fix a `math domain error` bug in the GleuScorer
#123
Tbabm
closed
3 years ago
0
call Scorer.cache_stats with src to align with the signature
#122
Tbabm
closed
3 years ago
0
Add GLEU scorer
#121
Tbabm
closed
3 years ago
1
[WIP] Add COMET scorer
#120
CoderPat
closed
3 years ago
2
stand-alone command line scorer
#119
neubig
closed
4 years ago
1
pip install does not auto-install requirements
#118
neubig
closed
2 years ago
1
Option to launch http server to view reports
#117
thammegowda
closed
4 years ago
3
Added summary-level rougeL scorer
#116
zdou0830
closed
4 years ago
1
Improvements to latex output
#115
madaan
closed
4 years ago
1
Bug in sentence level BLEU comparison
#114
madaan
opened
4 years ago
1
Fix a typo in README.md
#113
madaan
closed
4 years ago
1
Some measure of bucketed statistic reliability
#112
zdou0830
closed
4 years ago
5
Support pre-computing statistics for each system
#111
zdou0830
closed
5 years ago
4
Click through examples for source word reports
#110
neubig
closed
5 years ago
0
Fix sampling
#109
pmichel31415
closed
5 years ago
1
Bootstrap resampling without replacement
#108
pmichel31415
closed
5 years ago
5
Create examples of word buckets
#107
neubig
closed
5 years ago
0
Made tokenization on ascii spaces only
#106
neubig
closed
5 years ago
0
Better error checking when reading in alignments
#105
neubig
closed
5 years ago
0
Added word bucketer based on casing of words
#104
neubig
closed
5 years ago
0
Made count reading more robust
#103
neubig
closed
5 years ago
0
Fast Significance Test for SacreBLEU
#102
zdou0830
closed
5 years ago
0
Bump up version number to update pypi
#101
pmichel31415
closed
5 years ago
0
Support the latest version of matplotlib
#100
zdou0830
closed
5 years ago
1
Detokenized BLEU as new scorer type
#99
bricksdont
closed
5 years ago
12
Account for non-ASCII characters
#98
SebastinSanty
closed
5 years ago
1
Fix sentence bucketer for length difference
#97
neubig
closed
5 years ago
0
More informative error messages
#96
pmichel31415
closed
5 years ago
0
BLEU on a scale of 0 to 100
#95
pmichel31415
closed
5 years ago
4
Added ability to bucket sentences by external label
#94
zdou0830
closed
5 years ago
5
Added ability to name analyses
#93
zdou0830
closed
5 years ago
2
Ability to de-duplicate identical sentences
#92
zdou0830
closed
5 years ago
0
Add Meteor scorer
#91
zdou0830
closed
5 years ago
3
Ability to specify p-value threshold
#90
zdou0830
closed
5 years ago
5
Ability to bucket sentences by external label
#89
neubig
closed
5 years ago
0
Some measure of bucketed statistic reliability
#88
neubig
closed
4 years ago
2
Errors resulting from command line formatting can be opaque
#87
neubig
closed
5 years ago
0
Better documentation and util script for freq_counts file
#86
neubig
closed
5 years ago
0
Ability to name analyses
#85
neubig
closed
5 years ago
1
Next