Frame-semantic-transformer

Performance

* perf: minor performance improvements for arg extraction and frame detection (15)

* save best model chkpt based on val loss

* Adding loader setup to training

* add more optional config for loggers/callbacks during training

* adding explicit logging for test/train/val loss to end of epochs

* rever to default PL logging behavior if no loggers are provided

* adding helpers for model evaluations

* try to standardize arg extraction output

* standardize punct in args extraction

* use fast tokenizer for sent clenanup

* switch to just using tokenizer cleanup for speed

* run clean_up_tokenization just once before arg extraction, not for each arg

* fixing val_metrics err ([`7e03969`](https://github.com/chanind/frame-semantic-transformer/commit/7e039695b8cfa1ae5b8de1b9b4d4145e5bec3884))

Chore

* chore: remove poetry.lock from demo docker build ([`2f8ffb9`](https://github.com/chanind/frame-semantic-transformer/commit/2f8ffb99afa82f259db6043247d8b227a829a44a))

Fix

* fix: fixing errors when no frames are found (14) ([`ef2424c`](https://github.com/chanind/frame-semantic-transformer/commit/ef2424cba57515b9aa8205fe29f015b57f26504e))

Feature

* feat: adding support for running inference on multiple sentences in batches (11) ([`e6423e5`](https://github.com/chanind/frame-semantic-transformer/commit/e6423e594de22850d9ea6369f80ca9a0e81ac8e0))

Chore

* chore: fixing README badge after shields.io breaking change ([`bd90fef`](https://github.com/chanind/frame-semantic-transformer/commit/bd90fef60aa1ae96c672685f0315389ac6839651))

Feature

* feat: Multilingual training refactor (10)

* WIP refactoring to make it easier to train on different framenets

* Making evaluate runnable directly to evaluate pretrained models

* tweaking tests

* refactoring training / eval scripts

* add validation that loaders match model

* updating README

* cleaning up typing

* use 3.8 for CI

* updating semantic release ([`7bf7ae5`](https://github.com/chanind/frame-semantic-transformer/commit/7bf7ae5474cc586739f1ad77848e45db09ff5a0d))

Unknown

* fix typo in README (6) ([`a151e5a`](https://github.com/chanind/frame-semantic-transformer/commit/a151e5aaf87ef5ece2add1a68968cbde068a5d3c))

* Update README.md ([`461eced`](https://github.com/chanind/frame-semantic-transformer/commit/461eced8ea745b63154cff0c44a9d16d8be80812))

* Update README.md ([`a6f5001`](https://github.com/chanind/frame-semantic-transformer/commit/a6f500151baa241105fee05f22383b86d923d9f6))

Fix

* fix: updating README stats ([`76e4e75`](https://github.com/chanind/frame-semantic-transformer/commit/76e4e754b534389de9c86caced762461ae884e88))

Feature

* feat: Frame classification hints (3)

* adding in lexical unit data for smarter frame classification

* adding in stemming for lu handling

* allow skipping validation in initial epochs for faster training

* use self.current_epoch instead of batch_idx

* using bigrams to reduce the amount of frame suggestions

* refactoring bigrams stuff and adding more tests

* fixing bug with trigger bigrams

* updating README

* updating model revision ([`201ed51`](https://github.com/chanind/frame-semantic-transformer/commit/201ed517c7a78b32d659150dadf11fcd7b4fea6d))

Unknown

* fixing typo in demo server ([`a15ef6d`](https://github.com/chanind/frame-semantic-transformer/commit/a15ef6da75483e016cb8959441ccf90e5ec79700))

* improving demo UI (4)

* improving demo UI

* adding secret &39;model&39; param to client ([`8bf3275`](https://github.com/chanind/frame-semantic-transformer/commit/8bf327592f406b821bee2dca9fb58d85b0b200ab))

* UI improvements for demo ([`69e85af`](https://github.com/chanind/frame-semantic-transformer/commit/69e85afc30e4835f2fdd5bc7f5cd6dbb7a8b021a))