Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

WIP: Multilabel classification #440

Merged
merged 35 commits into from
May 11, 2024
Merged

WIP: Multilabel classification #440

merged 35 commits into from
May 11, 2024

Commits on Apr 19, 2024

  1. Added Multilabel kNN classification evaluator

    @x-tabdeveloping
    x-tabdeveloping committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    d42ef56 View commit details
    Browse the repository at this point in the history

  2. Added Multilabel classification AbsTask

    @x-tabdeveloping
    x-tabdeveloping committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    2da53e2 View commit details
    Browse the repository at this point in the history

  3. Added MultiLabelClassification Task type to TaskMetadata

    @x-tabdeveloping
    x-tabdeveloping committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    e22c9e6 View commit details
    Browse the repository at this point in the history

  4. bugfix

    @x-tabdeveloping
    x-tabdeveloping committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    6bdd3f5 View commit details
    Browse the repository at this point in the history

Commits on Apr 23, 2024

  1. Removed all references to metadata_dict from Multilabel classification

    @x-tabdeveloping
    x-tabdeveloping committed Apr 23, 2024
    Configuration menu
    Copy the full SHA
    a31ed01 View commit details
    Browse the repository at this point in the history

  2. Added Eurlex (wip)

    @x-tabdeveloping
    x-tabdeveloping committed Apr 23, 2024
    Configuration menu
    Copy the full SHA
    3b30b50 View commit details
    Browse the repository at this point in the history

Commits on Apr 24, 2024

  1. Made MultiLabelClassification more efficient by moving the embedding … 

    …step outside the evaluator and encoding every possible training sentence before running the evaluation.
    @x-tabdeveloping
    x-tabdeveloping committed Apr 24, 2024
    Configuration menu
    Copy the full SHA
    4ade123 View commit details
    Browse the repository at this point in the history

  2. fix: changed itertools.chain to itertools.chain.from_iter

    @x-tabdeveloping
    x-tabdeveloping committed Apr 24, 2024
    Configuration menu
    Copy the full SHA
    c6217db View commit details
    Browse the repository at this point in the history

  3. fix: Fixed validation and import on MultiEURLEX

    @x-tabdeveloping
    x-tabdeveloping committed Apr 24, 2024
    Configuration menu
    Copy the full SHA
    e2a0b1d View commit details
    Browse the repository at this point in the history

  4. Merge branch 'main' into multilabel-classification

    @x-tabdeveloping
    x-tabdeveloping committed Apr 24, 2024
    Configuration menu
    Copy the full SHA
    b342b3d View commit details
    Browse the repository at this point in the history

Commits on Apr 25, 2024

  1. Removed MultioutputClassifier, because kNN can already do that

    @x-tabdeveloping
    x-tabdeveloping committed Apr 25, 2024
    Configuration menu
    Copy the full SHA
    ad955d1 View commit details
    Browse the repository at this point in the history

  2. fix: multilabels are not turned into an array

    @x-tabdeveloping
    x-tabdeveloping committed Apr 25, 2024
    Configuration menu
    Copy the full SHA
    b5e99c8 View commit details
    Browse the repository at this point in the history

  3. Ran linting

    @x-tabdeveloping
    x-tabdeveloping committed Apr 25, 2024
    Configuration menu
    Copy the full SHA
    9381852 View commit details
    Browse the repository at this point in the history

Commits on Apr 26, 2024

  1. Added points for PR (2+23*4 for eurlex, 10 for new task type)

    @x-tabdeveloping
    x-tabdeveloping committed Apr 26, 2024
    Configuration menu
    Copy the full SHA
    d122507 View commit details
    Browse the repository at this point in the history

Commits on Apr 29, 2024

  1. fix: Fixed undersampling for training set in Multitask classification

    @x-tabdeveloping
    x-tabdeveloping committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    623f7af View commit details
    Browse the repository at this point in the history

  2. fix: sped up sampling by using select() instead of indexing

    @x-tabdeveloping
    x-tabdeveloping committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    55efd8f View commit details
    Browse the repository at this point in the history

  3. fix: removed duplicate code for selecting train sentences

    @x-tabdeveloping
    x-tabdeveloping committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    7f87f96 View commit details
    Browse the repository at this point in the history

  4. Added n_samples and avg_length to MultiEURLEX

    @x-tabdeveloping
    x-tabdeveloping committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    052538b View commit details
    Browse the repository at this point in the history

  5. Added MultiEURLEX results for paraphrase-multilingual-MiniLM-L12

    @x-tabdeveloping
    x-tabdeveloping committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    0bf888b View commit details
    Browse the repository at this point in the history

Commits on May 3, 2024

  1. Added EURLEX results for multilingual-e5-small

    @x-tabdeveloping
    x-tabdeveloping committed May 3, 2024
    Configuration menu
    Copy the full SHA
    1802201 View commit details
    Browse the repository at this point in the history

  2. Changed evaluation in multilabel classification to use MLPClassifier

    @x-tabdeveloping
    x-tabdeveloping committed May 3, 2024
    Configuration menu
    Copy the full SHA
    f575fcb View commit details
    Browse the repository at this point in the history

Commits on May 8, 2024

  1. Limited evaluation to test split in EURLEX

    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    3248b70 View commit details
    Browse the repository at this point in the history

  2. multilabel classification now subsamples test set, and the neural net… 

    …work is smaller.
    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    5cd605b View commit details
    Browse the repository at this point in the history

  3. Multilabel classification now allows tasks to define the samples per … 

    …label for training
    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    45bfa29 View commit details
    Browse the repository at this point in the history

  4. Removed unused code

    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    33f3f27 View commit details
    Browse the repository at this point in the history

  5. Moved subsampling to before encoding

    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    0117b59 View commit details
    Browse the repository at this point in the history

  6. Made subsampling error tolerant

    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    49afeb1 View commit details
    Browse the repository at this point in the history

  7. Made sure all labels are represented in the training set

    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    96312c7 View commit details
    Browse the repository at this point in the history

  8. Revert "Made sure all labels are represented in the training set" 

    This reverts commit 96312c7.
    @x-tabdeveloping
    x-tabdeveloping committed May 8, 2024
    Configuration menu
    Copy the full SHA
    f55cbeb View commit details
    Browse the repository at this point in the history

Commits on May 9, 2024

  1. Reran EURLEX

    @x-tabdeveloping
    x-tabdeveloping committed May 9, 2024
    Configuration menu
    Copy the full SHA
    87ad125 View commit details
    Browse the repository at this point in the history

  2. EURLEX only evaluates on test set, not validation set

    @x-tabdeveloping
    x-tabdeveloping committed May 9, 2024
    Configuration menu
    Copy the full SHA
    6d2d1b0 View commit details
    Browse the repository at this point in the history

  3. Made KNeighbours the default classifier in MultiLabelClassification, … 

    …made switching out classifiers more flexible
    @x-tabdeveloping
    x-tabdeveloping committed May 9, 2024
    Configuration menu
    Copy the full SHA
    51ccdc4 View commit details
    Browse the repository at this point in the history

  4. Merge branch 'multilabel-classification' of https://github.com/embedd… 

    …ings-benchmark/mteb into multilabel-classification
    @x-tabdeveloping
    x-tabdeveloping committed May 9, 2024
    Configuration menu
    Copy the full SHA
    1dad403 View commit details
    Browse the repository at this point in the history

  5. Added results for EURLEX

    @x-tabdeveloping
    x-tabdeveloping committed May 9, 2024
    Configuration menu
    Copy the full SHA
    55374a9 View commit details
    Browse the repository at this point in the history

Commits on May 11, 2024

  1. Merge branch 'main' into multilabel-classification

    @x-tabdeveloping
    x-tabdeveloping committed May 11, 2024
    Configuration menu
    Copy the full SHA
    e617020 View commit details
    Browse the repository at this point in the history