Mteb

Fix

* fix: Add new languages to NTREX (543)

* Add 21 additional (new) languages to NTREX

* Improved subsampling of language pairs

* add results

* added points: 21 new languages to NTREX -> 84 points

* fixed review suggestions

* add results for all-MiniLM-L6

* lint fix

* add results for 1997

* lint fix

* update points

---------

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com> ([`809e1ee`](https://github.com/embeddings-benchmark/mteb/commit/809e1ee0a4ba016c6ae35c925f55aa737a9224a8))

Unknown

* Update tasks table ([`9e091cf`](https://github.com/embeddings-benchmark/mteb/commit/9e091cf3f554d636a979f7c2b55f0323c87733e6))

* Update points table ([`210efe3`](https://github.com/embeddings-benchmark/mteb/commit/210efe3171bcc6f0a985a5c012bba08ae29b5ce0))

Fix

* fix: Fast loading for cross lingual tasks (572)

* fast loading for bitext mining

* lint

* consistency

* bump datasets version

* add polars dependency

* loader mixin

* documentation for fast loading

* detail

* fix tests

* tatoeba dataset in mteb org

* added points

---------

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com> ([`aa2ffe8`](https://github.com/embeddings-benchmark/mteb/commit/aa2ffe8dad092bb333260148652cfad67cf757c7))

Unknown

* Update points table ([`b011ae3`](https://github.com/embeddings-benchmark/mteb/commit/b011ae3aa857503543c8a4c7b7f2efa49f7c0172))

* Update points table ([`08800ad`](https://github.com/embeddings-benchmark/mteb/commit/08800adb975cd3d800132559a94117e844f3f2c6))

* get_task now filters languages in multilingual tasks (604)

* bugfix language in bibleNLP

* Added deep language filtering

* added points

* removed extra lines from jsonl file

---------

Co-authored-by: Imene Kerboua <33312980+imenelydiakerusers.noreply.github.com> ([`8f69a34`](https://github.com/embeddings-benchmark/mteb/commit/8f69a34449428f24872f2717703dab7cf7b7071a))

Fix

* fix: Add sentiment classification datasets as one multilingual task (575)

* fix: add multlingual sentiment classification

* fix: remove old tasks and fix typo

* chore: add nb samples

* chore:update comment

* chore: remove useless import

* add Welsh train split

* fix: add linting

* chore: add points and remove old eval files ([`ef53f68`](https://github.com/embeddings-benchmark/mteb/commit/ef53f6898d4c184771d2f4f2b56e21361ffaa2de))

Unknown

* Update tasks table ([`39f90eb`](https://github.com/embeddings-benchmark/mteb/commit/39f90eb97281e2f9c49037b83907322e16107fd4))

* Update points table ([`46f1701`](https://github.com/embeddings-benchmark/mteb/commit/46f1701b0ff581f8a3460dca1018021396febd9d))

Fix

* fix: Add LegalBench datasets - 3 (579)

* Add datasets

* Move LegalBench datasets to single file

* Add points

* Combine PC datasets

* Remove redundant PC results

---------

Co-authored-by: Imene Kerboua <33312980+imenelydiakerusers.noreply.github.com> ([`07b04e6`](https://github.com/embeddings-benchmark/mteb/commit/07b04e683bdb836948a973c2e106b993d7e38dc7))

Unknown

* Update tasks table ([`b519042`](https://github.com/embeddings-benchmark/mteb/commit/b519042a28c5e4e875c66000036dc19b9408fa6c))

* Update points table ([`0a373b0`](https://github.com/embeddings-benchmark/mteb/commit/0a373b0e9736555a2c2ba2f2f301ab6123127b7d))

Documentation

* docs: fixed error in points ([`6385153`](https://github.com/embeddings-benchmark/mteb/commit/638515361ca37e2b6c684abf72c9d359cf2f2ffe))

Fix

* fix: TweetTopicSingleClassification added (603)

* TweetTopicSingleClassification added
* Update mteb/tasks/Classification/eng/TweetTopicSingleClassification.py
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com>
* Update mteb/tasks/Classification/eng/TweetTopicSingleClassification.py
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com>
* TweetTopicSingleClassification points added
---------
Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com>
Co-authored-by: Isaac Chung <chungisaac1217gmail.com> ([`ec2579e`](https://github.com/embeddings-benchmark/mteb/commit/ec2579e0c0be10ecc4561d99ebc0372eb02cce9c))

Unknown

* Update points table ([`8e19d10`](https://github.com/embeddings-benchmark/mteb/commit/8e19d10786f7b6eed7d7d430a12a3d7c0123f3fd))

* Update points table ([`99d17f0`](https://github.com/embeddings-benchmark/mteb/commit/99d17f0427edd3240da2832c1a8dbf5d3c01b66d))

* Update tasks table ([`8aa4de2`](https://github.com/embeddings-benchmark/mteb/commit/8aa4de20f3b6e3f70afabb32b6a5ea7042419aee))

* Add Spanish Sentiment dataset (539)

* add spanish sentiment dataset

* PR comments

* add points

* PR comments

Co-authored-by: Imene Kerboua <33312980+imenelydiakerusers.noreply.github.com>

---------

Co-authored-by: Imene Kerboua <33312980+imenelydiakerusers.noreply.github.com> ([`cac06fa`](https://github.com/embeddings-benchmark/mteb/commit/cac06fa7bdec20224f909208dcaa66a9ae0a8b83))

Fix

* fix: Add Multiple Sentiment/Hate Speech Classification Datasets (598)

* new dataset GermanPoliticiansTwitterSentiment

* add HateSpeechPortugueseClassification dataset (new language)

* Added multilingual tweet sentiment classification dataset (8 languages, 1 new)

* update points

* Rename 595.jsonl to 598.jsonl

* update files

* update files

* make lint

* update scores

* Update mteb/tasks/Classification/multilingual/TweetSentimentClassification.py

* Update mteb/tasks/Classification/por/HateSpeechPortugueseClassification.py

* update scores

---------

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsengmail.com> ([`9db1dde`](https://github.com/embeddings-benchmark/mteb/commit/9db1dde9dfd2c099a252c1fd199afd73996f8b45))

Unknown

* Update tasks table ([`0a28e82`](https://github.com/embeddings-benchmark/mteb/commit/0a28e82eacf3de42bda071db0cf7990be4f33b11))