From a8054e64a2c1913e3ea859a61e8b53fe4be41b26 Mon Sep 17 00:00:00 2001 From: Marcin Kardas Date: Thu, 7 May 2020 15:51:18 +0100 Subject: [PATCH] Update README --- README.md | 8 +++-- notebooks/training/lm.ipynb | 34 +++++++++++++++++++ notebooks/training/table-segmentation.ipynb | 34 +++++++++++++++++++ .../training/table-type-classifier.ipynb | 34 +++++++++++++++++++ 4 files changed, 107 insertions(+), 3 deletions(-) create mode 100644 notebooks/training/lm.ipynb create mode 100644 notebooks/training/table-segmentation.ipynb create mode 100644 notebooks/training/table-type-classifier.ipynb diff --git a/README.md b/README.md index c54e8d6..607ec65 100644 --- a/README.md +++ b/README.md @@ -23,14 +23,16 @@ We publish the following datasets: * [PWCLeaderboards](https://github.com/paperswithcode/axcell/releases/download/v1.0/pwc-leaderboards.json.xz) See [datasets](notebooks/datasets.ipynb) notebook for an example of how to load the datasets provided below. The [extraction](notebooks/extraction.ipynb) notebook shows how to use `axcell` to extract text and tables from papers. -## Training - - ## Evaluation See the [evaluation](notebooks/evaluation.ipynb) notebook for the full example on how to evaluate AxCell on the PWCLeaderboards dataset. +## Training + +* [pre-training language model](notebooks/training/lm.ipynb) on the ArxivPapers dataset +* [table type classifier](notebooks/training/table-type-classifier.ipynb) and [table segmentation](notebooks/training/table-segmentation.ipynb) on the SegmentedResults dataset + ## Pre-trained Models You can download pretrained models here: diff --git a/notebooks/training/lm.ipynb b/notebooks/training/lm.ipynb new file mode 100644 index 0000000..e9c9d18 --- /dev/null +++ b/notebooks/training/lm.ipynb @@ -0,0 +1,34 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Language Model Pre-training\n", + "\n", + "Coming soon" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/notebooks/training/table-segmentation.ipynb b/notebooks/training/table-segmentation.ipynb new file mode 100644 index 0000000..f6aa91f --- /dev/null +++ b/notebooks/training/table-segmentation.ipynb @@ -0,0 +1,34 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Table Segmentation Training\n", + "\n", + "Coming soon" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/notebooks/training/table-type-classifier.ipynb b/notebooks/training/table-type-classifier.ipynb new file mode 100644 index 0000000..a7471bc --- /dev/null +++ b/notebooks/training/table-type-classifier.ipynb @@ -0,0 +1,34 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Table Type Classifier Training \n", + "\n", + "Coming soon" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}