Giters
obss
/
jury
Comprehensive NLP Evaluation System
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
185
Watchers:
5
Issues:
49
Forks:
20
obss/jury Issues
ValueError: unmarshallable object
Closed
a month ago
Comments count
5
Meteor for multiple languages
Updated
8 months ago
Comments count
1
Drop Python 3.7 Support
Closed
a year ago
[BUG] requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/wmt21-cometinho-da/revision/main
Closed
a year ago
Comments count
3
ZeroDivisionError: division by zero in AccuracyForLanguageGeneration._compute_single_pred_single_ref
Closed
a year ago
Comments count
3
[BUG] AttributeError: 'DownloadConfig' object has no attribute 'storage_options'
Closed
a year ago
Comments count
5
Fix `sklearn` dependency
Closed
2 years ago
BLEURT is failing to produce results
Updated
2 years ago
Comments count
4
Move infrastructure to new `evaluate` package (from `datasets`)
Closed
2 years ago
ModuleNotFoundError: No module named 'validators'
Closed
2 years ago
Refactor docstrings, typo-check, review imports
Closed
2 years ago
Add COMET
Closed
2 years ago
Prism support for use_cuda option
Updated
3 years ago
Add CHRF
Closed
3 years ago
Add TER
Closed
3 years ago
Add WER
Closed
3 years ago
Add license information for BLEURT and Prism
Closed
3 years ago
New Metric: Add BARTScore
Closed
3 years ago
New source for Prism model
Closed
3 years ago
New Metric: CER
Closed
3 years ago
Nltk version upgrade for >=3.6.6
Closed
3 years ago
Refactor all metrics to use dl_manager internally
Closed
3 years ago
Add support for BERTScore to 0.3.11
Closed
3 years ago
Comments count
1
New Metric: Prism
Closed
3 years ago
Add citation for the project (zenodo)
Closed
3 years ago
New metric: Add BLEURT
Closed
3 years ago
BLEU metric calculates wrong results for single hypothesis single reference pairs.
Closed
3 years ago
Add support for custom tokenizer for BLEU
Updated
3 years ago
load_metric by path (relative/absolute)
Closed
3 years ago
Facing datasets error
Closed
3 years ago
Comments count
8
Discard empty corpus before computation
Closed
3 years ago
BLEU: ndarray reshape error
Closed
3 years ago
Comments count
4
Understanding BLEU Score ('bleu_n')
Closed
3 years ago
Comments count
4
Upgrade nltk>=3.6.4
Closed
3 years ago
Read support from a folder
Closed
3 years ago
Computing BLEU more than once
Closed
3 years ago
Comments count
4
Metrics for different tasks
Closed
3 years ago
Adopt arrow implementation from datasets
Closed
3 years ago
Implementing fixtures for test cases.
Closed
3 years ago
Add multiple ref handle for squad
Closed
3 years ago
CLI Implementation
Closed
3 years ago
Comments count
5
Bug: Metric object and string cannot be used together in input.
Closed
3 years ago
Comments count
1
demo notebook
Closed
3 years ago
Comments count
2
Add QA metrics (squad) to the current system.
Closed
3 years ago
Imrpove metric definitions
Closed
3 years ago
Add reduce_fn parameter
Closed
3 years ago
Comments count
1
README.md update elaborating usage.
Closed
3 years ago
Comments count
1
Multiple predictions and multiple references
Closed
3 years ago
usage in readme
Closed
3 years ago