Unitxt

What's Changed
* Change formats to be backward compatible by elronbandel in https://github.com/IBM/unitxt/pull/453


**Full Changelog**: https://github.com/IBM/unitxt/compare/1.4.2...1.4.3

Enhancements
* Added ability to calculate confidence interval for additional scores beyond the main_score by assaftibm in https://github.com/IBM/unitxt/pull/431
* Improved error messaging in test cards and added option to disable via environment variable by yoavkatz in https://github.com/IBM/unitxt/pull/440
* Added support for Japanese language in sacrebleu by yoavkatz in https://github.com/IBM/unitxt/pull/433
* Introduced binary recall, precision metrics, and advanced filtering operators by lilacheden in https://github.com/IBM/unitxt/pull/424
* Added text completion task and modified lm harness template by perlitz in https://github.com/IBM/unitxt/pull/429

Internal code changes
* Converted instructions to operators by elronbandel in https://github.com/IBM/unitxt/pull/450

Bug fixes
* Fixed split definition in debater datasets by ilyashnil in https://github.com/IBM/unitxt/pull/443
* Added new requirements for sacrebleu by gitMichal in https://github.com/IBM/unitxt/pull/448

Documentation
* Documented release notes process by matanor in https://github.com/IBM/unitxt/pull/444
* Added guidelines for updating Unitxt documentation by matanor in https://github.com/IBM/unitxt/pull/446

Non backward compatible changes
* Implemented SystemFormat instance operator and updated BasicRecipe to use all operators, removing renderers and ICLFormat by dafnapension in https://github.com/IBM/unitxt/pull/423
(this change can break any code using the deprecated ICLFormat)
* Additional verification introduced, aiming for uniquely determined results by dafnapension in https://github.com/IBM/unitxt/pull/435

New Contributors
* lilacheden made their first contribution in https://github.com/IBM/unitxt/pull/424

**Full Changelog**: https://github.com/IBM/unitxt/compare/1.4.1...1.4.2

(Same as 1.4.0 - rereleasing due to release process error)

Enhancements

* New random generation mechanism to remove dependency between different random generators matanor in https://github.com/IBM/unitxt/pull/414
* New MultipleChoiceTemplate which changes all QA datasets by elronbandel in https://github.com/IBM/unitxt/pull/405
* New MAP, MRR, and RetrievalK metrics by assaftibm in https://github.com/IBM/unitxt/pull/422
* New LoadFromKaggle loader which allows direct loading of datasets from Kaggle by ilyashnil in https://github.com/IBM/unitxt/pull/413
* New StringContainment metric that if one of the references is contained in the prediction by ellarabi in https://github.com/IBM/unitxt/pull/394
* New ConvertToBoolean post processor that changes the predict to either TRUE or FALSE by ellarabi in https://github.com/IBM/unitxt/pull/394
* 15 new open source classification datasets by ilyashnil in https://github.com/IBM/unitxt/pull/410, https://github.com/IBM/unitxt/pull/418
* Documentation is now automatically generate in each release (https://github.com/IBM/unitxt/pull/384)

Bug fixes
* Fixed and improved error checking in multi label F1 by yoavkatz in https://github.com/IBM/unitxt/pull/390
* Changed translations to use normalized_sacrebleu by gitMichal in https://github.com/IBM/unitxt/pull/426

Non backward compatible changes
* MultipleChoice QA datasets need to move to new MultipleChoiceTemplates
* Translation blue metric is now between 0-1 and not 0-100
* New randomization mechanism may change selects selection of demos , randomized text augmentation, or any other random choice.

What's Changed
* metric and processor related to robustness evaluation by ellarabi in https://github.com/IBM/unitxt/pull/394
* Removed variable set in debugging by yoavkatz in https://github.com/IBM/unitxt/pull/409
* Adding simple datasets by ilyashnil in https://github.com/IBM/unitxt/pull/410
* Add multiple choice template and fix mmlu by elronbandel in https://github.com/IBM/unitxt/pull/405
* Fixed error check in multi label F1 by yoavkatz in https://github.com/IBM/unitxt/pull/390
* FIX multiple choice template by perlitz in https://github.com/IBM/unitxt/pull/416
* example of kaggle loader by ilyashnil in https://github.com/IBM/unitxt/pull/413
* Medical abstract by ilyashnil in https://github.com/IBM/unitxt/pull/418
* Multilabel and jsons by ilyashnil in https://github.com/IBM/unitxt/pull/419
* Improve dataset addition tutorial + Fix auto uploads of the catalog to the web by elronbandel in https://github.com/IBM/unitxt/pull/384
* Improve docs by elronbandel in https://github.com/IBM/unitxt/pull/420
* Fix docs and docs compilation tests by elronbandel in https://github.com/IBM/unitxt/pull/421
* Hard code classes names by elronbandel in https://github.com/IBM/unitxt/pull/425
* Retrieval metrics by assaftibm in https://github.com/IBM/unitxt/pull/422
* modify to different bleu impl. by gitMichal in https://github.com/IBM/unitxt/pull/426
* Improve docs by elronbandel in https://github.com/IBM/unitxt/pull/427
* Independent random generators by matanor in https://github.com/IBM/unitxt/pull/414

New Contributors
* ellarabi made their first contribution in https://github.com/IBM/unitxt/pull/394

**Full Changelog**: https://github.com/IBM/unitxt/compare/1.3.1...1.4.0

Enhancements

* New random generation mechanism to remove dependency between different random generators matanor in https://github.com/IBM/unitxt/pull/414
* New MultipleChoiceTemplate which changes all QA datasets by elronbandel in https://github.com/IBM/unitxt/pull/405
* New MAP, MRR, and RetrievalK metrics by assaftibm in https://github.com/IBM/unitxt/pull/422
* New LoadFromKaggle loader which allows direct loading of datasets from Kaggle by ilyashnil in https://github.com/IBM/unitxt/pull/413
* New StringContainment metric that if one of the references is contained in the prediction by ellarabi in https://github.com/IBM/unitxt/pull/394
* New ConvertToBoolean post processor that changes the predict to either TRUE or FALSE by ellarabi in https://github.com/IBM/unitxt/pull/394
* 15 new open source classification datasets by ilyashnil in https://github.com/IBM/unitxt/pull/410, https://github.com/IBM/unitxt/pull/418
* Documentation is now automatically generate in each release (https://github.com/IBM/unitxt/pull/384)

Bug fixes
* Fixed and improved error checking in multi label F1 by yoavkatz in https://github.com/IBM/unitxt/pull/390
* Changed translations to use normalized_sacrebleu by gitMichal in https://github.com/IBM/unitxt/pull/426

Non backward compatible changes
* MultipleChoice QA datasets need to move to new MultipleChoiceTemplates
* Translation blue metric is now between 0-1 and not 0-100
* New randomization mechanism may change selects selection of demos , randomized text augmentation, or any other random choice.

What's Changed
* metric and processor related to robustness evaluation by ellarabi in https://github.com/IBM/unitxt/pull/394
* Removed variable set in debugging by yoavkatz in https://github.com/IBM/unitxt/pull/409
* Adding simple datasets by ilyashnil in https://github.com/IBM/unitxt/pull/410
* Add multiple choice template and fix mmlu by elronbandel in https://github.com/IBM/unitxt/pull/405
* Fixed error check in multi label F1 by yoavkatz in https://github.com/IBM/unitxt/pull/390
* FIX multiple choice template by perlitz in https://github.com/IBM/unitxt/pull/416
* example of kaggle loader by ilyashnil in https://github.com/IBM/unitxt/pull/413
* Medical abstract by ilyashnil in https://github.com/IBM/unitxt/pull/418
* Multilabel and jsons by ilyashnil in https://github.com/IBM/unitxt/pull/419
* Improve dataset addition tutorial + Fix auto uploads of the catalog to the web by elronbandel in https://github.com/IBM/unitxt/pull/384
* Improve docs by elronbandel in https://github.com/IBM/unitxt/pull/420
* Fix docs and docs compilation tests by elronbandel in https://github.com/IBM/unitxt/pull/421
* Hard code classes names by elronbandel in https://github.com/IBM/unitxt/pull/425
* Retrieval metrics by assaftibm in https://github.com/IBM/unitxt/pull/422
* modify to different bleu impl. by gitMichal in https://github.com/IBM/unitxt/pull/426
* Improve docs by elronbandel in https://github.com/IBM/unitxt/pull/427
* Independent random generators by matanor in https://github.com/IBM/unitxt/pull/414

New Contributors
* ellarabi made their first contribution in https://github.com/IBM/unitxt/pull/394

**Full Changelog**: https://github.com/IBM/unitxt/compare/1.3.1...1.4.0

Enhancements

* Add classification datasets by ilyashnil in https://github.com/IBM/unitxt/pull/410
* Added StringContainment metric and convert_to_boolean post processor that normalizes "yes/no/true/false" by ellarabi in https://github.com/IBM/unitxt/pull/394

Bug fixes

* Fix for AugmentPrefixSuffix that ignored labels field by yoavkatz in https://github.com/IBM/unitxt/pull/409

What's Changed
* metric and processor related to robustness evaluation by ellarabi in https://github.com/IBM/unitxt/pull/394
* Removed variable set in debugging by yoavkatz in https://github.com/IBM/unitxt/pull/409
* Adding simple datasets by ilyashnil in https://github.com/IBM/unitxt/pull/410

New Contributors
* ellarabi made their first contribution in https://github.com/IBM/unitxt/pull/394

**Full Changelog**: https://github.com/IBM/unitxt/compare/1.3.1...1.3.2

Enhancements:

* FilterByValue can filter out instances that contain a given value (elronbandel) https://github.com/IBM/unitxt/pull/402
* added ag_news by (ilyashnil) in https://github.com/IBM/unitxt/pull/400

Fixes:

* DiverseLabelSampler used in balancing demonstrations in NER , binary and multi-label classification receives input field to balance on.(yoavkatz) https://github.com/IBM/unitxt/pull/399
* Fix to allow override empty_label of multi_label template used in non-english templates. (yoavkatz) https://github.com/IBM/unitxt/pull/403
* Fix to AugmentorPrefixSuffix not return same prefix/suffix repeated (yoavkatz) in https://github.com/IBM/unitxt/pull/407

Possible changes

- NER results will improve due to better balancing(yoavkatz) https://github.com/IBM/unitxt/pull/399

Documentation

* expand code coverage and documentation of refiner classes by (dafnapension) https://github.com/IBM/unitxt/pull/396


What's Changed
* added ag_news by ilyashnil in https://github.com/IBM/unitxt/pull/400
* peek at the first instance by dafnapension in https://github.com/IBM/unitxt/pull/401
* DiverseLabelsSampler fix by yoavkatz in https://github.com/IBM/unitxt/pull/399
* Enhance FilterByValue to have disallowed_values by elronbandel in https://github.com/IBM/unitxt/pull/402
* expand code coverage and documentation of refiner classes by dafnapension in https://github.com/IBM/unitxt/pull/396
* Also added more tests and documentation to DiverseLabelsSampler by yoavkatz in https://github.com/IBM/unitxt/pull/404
* Fix to allow override empty_label of multi_label template. by yoavkatz in https://github.com/IBM/unitxt/pull/403
* Fix suffix prefix not return same prefix/suffix repeated by yoavkatz in https://github.com/IBM/unitxt/pull/407

New Contributors
* ilyashnil made their first contribution in https://github.com/IBM/unitxt/pull/400

**Full Changelog**: https://github.com/IBM/unitxt/compare/1.3.0...1.3.1