TLDR-642 FinTOC benchmarks #426

NastyBoget · 2024-04-25T12:57:48Z

Added training scripts for the FinTOC 2022 Shared task (https://wp.lancs.ac.uk/cfie/fintoc2022/)
Added fintoc structure type and documentation for it

dedoc/structure_extractors/concrete_structure_extractors/fintoc_structure_extractor.py

dedoc/structure_extractors/feature_extractors/paired_feature_extractor.py

dedoc/structure_extractors/line_type_classifiers/fintoc_classifier.py

dedoc/structure_extractors/feature_extractors/fintoc_feature_extractor.py

scripts/fintoc2022/dataset_loader.py

scripts/fintoc2022/trainer.py

docs/source/parameters/structure_type.rst

docs/source/dedoc_api_usage/api.rst

docs/source/structure_types/fintoc.rst

* TLDR-659 added references to nodes into HTML return format (#427) * TLDR-660 fixes in article type (#428) * TLDR-642 FinTOC benchmarks (#426) * TLDR-657 remove other_fields from LineMetadata and DocumentMetadata (#430) * Readme fixes (#431) * new version 2.2.1 (#432)

NastyBoget added 6 commits April 18, 2024 18:04

Add fintoc scripts (work in progress)

cc5f45c

Big refactoring of fintoc scripts

be31fca

Fix some bugs and write documentation

3d47214

Add classifiers downloading, small fixes

4e3822f

FinTOC benchmarks added and all classifiers uploaded to huggingface

751e0b5

Added structure type documentation and tests

c693de1

NastyBoget requested a review from oksidgy April 25, 2024 12:57

NastyBoget self-assigned this Apr 25, 2024