Simple, type-safe access to the TARGER neural argument tagging APIs.
With this package you can analyze the argumentative structures using one of the pre-trained neural models for argument mining found in the TARGER API. The API is hosted by the Webis research group and free to use.
pip install targer-api
from targer_api import analyze_text
arguments = analyze_text(
"The alternative vote is advantageous. "
"The President is directly elected by secret ballot "
"under the system of the Alternative Vote."
)
print(arguments)
If you use this package, please cite the paper from the TARGER authors. You can use the following BibTeX information for citation:
@InProceedings{chernodub:2019,
author = {Artem Chernodub and Oleksiy Oliynyk and Philipp Heidenreich and Alexander Bondarenko and Matthias Hagen and Chris Biemann and Alexander Panchenko},
booktitle = {57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)},
editor = {{Martha R.} {Costa-juss{\`a}} and Enrique Alfonseca},
ids = {bondarenko:2019b},
month = jul,
pages = {195-200},
publisher = {Association for Computational Linguistics},
site = {Florence, Italy},
title = {{TARGER: Neural Argument Mining at Your Fingertips}},
url = {https://www.aclweb.org/anthology/P19-3031},
year = 2019
}
To build and develop this package you need to install the build
package:
pip install build
Install package dependencies:
pip install -e .
Install test dependencies:
pip install -e .[test]
Verify your changes against the test suite to verify.
flake8 targer_api tests examples
pylint -E targer_api tests examples
pytest targer_api tests examples
Please also add tests for the axioms or integrations you've added.
A wheel for this package can be built by:
python -m build
This repository is released under the MIT license.