Catbird is an open source paraphrase generation toolkit based on PyTorch.

Catbird is an open source paraphrase generation toolkit based on PyTorch.

Quick Start

Requirements and Installation

The project is based on PyTorch 1.5+ and Python 3.6+.

Install Catbird

The package can be installed using pip:

pip install catbird

This does not include configuration files or tools. Alternatively, you can run from the source code:

a. Clone the repository.

git clone https://github.com/AfonsoSalgadoSousa/catbird.git

b. Install dependencies. This project uses Poetry as its package manager. There should Make sure you have it installed. For more info check Poetry's official documentation. To install dependencies, simply run:

poetry install

Dataset Preparation

For now, we only work with the Quora Question Pairs dataset. It is recommended to download and extract the datasets somewhere outside the project directory and symlink the dataset root to $CATBIRD/data as below. If your folder structure is different, you may need to change the corresponding paths in config files.

catbird
├── catbird
├── tools
├── configs
├── data
│   ├── quora
│   │   ├── quora_duplicate_questions.tsv

We use the HuggingFace Datasets library to load the datasets.

Train

poetry run python tools/train.py ${CONFIG_FILE} [optional arguments]

Example:

1. Train T5 on QQP.

$ python tools/train.py configs/t5_quora.yaml

Contributors

• Afonso Sousa ([email protected])