| Name | metametric JSON |
| Version |
0.2.1
JSON |
| download |
| home_page | None |
| Summary | A Unified View of Evaluation Metrics for Structured Prediction |
| upload_time | 2024-11-05 04:53:43 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# metametric
The `metametric` Python package offers a set of tools for quickly and easily defining and implementing evaluation metrics for a variety of structured prediction tasks in natural language processing (NLP) based on the framework presented in the following paper:
> [A Unified View of Evaluation Metrics for Structured Prediction](https://arxiv.org/abs/2310.13793). Yunmo Chen, William Gantt, Tongfei Chen, Aaron Steven White, and Benjamin Van Durme. *EMNLP 2023*.
The key features of the package include:
- A decorator for automatically defining and implementing a custom metric for an arbitrary `dataclass`.
- A collection of generic components for defining arbitrary new metrics based on the framework in the paper.
- Implementations of a number of metrics for common structured prediction tasks.
To install, run:
```bash
pip install metametric
```
If you use this codebase in your work, please cite the following paper:
```tex
@inproceedings{metametric,
title={A Unified View of Evaluation Metrics for Structured Prediction},
author={Yunmo Chen and William Gantt and Tongfei Chen and Aaron Steven White and Benjamin {Van Durme}},
booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
address={Singapore},
}
```
Raw data
{
"_id": null,
"home_page": null,
"name": "metametric",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Tongfei Chen <tongfei@pm.me>, Yunmo Chen <chanwanmok@gmail.com>, Will Gantt <wgantt.iv@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/ed/7d/54af7e1c4fca7bbfe50ea07c78d0c1f8e1d14dbd5c004f8ce0b17ad8dfda/metametric-0.2.1.tar.gz",
"platform": null,
"description": "# metametric\n\nThe `metametric` Python package offers a set of tools for quickly and easily defining and implementing evaluation metrics for a variety of structured prediction tasks in natural language processing (NLP) based on the framework presented in the following paper:\n\n> [A Unified View of Evaluation Metrics for Structured Prediction](https://arxiv.org/abs/2310.13793). Yunmo Chen, William Gantt, Tongfei Chen, Aaron Steven White, and Benjamin Van Durme. *EMNLP 2023*.\n\nThe key features of the package include:\n\n- A decorator for automatically defining and implementing a custom metric for an arbitrary `dataclass`.\n- A collection of generic components for defining arbitrary new metrics based on the framework in the paper.\n- Implementations of a number of metrics for common structured prediction tasks.\n\n\nTo install, run:\n```bash\npip install metametric\n```\n\nIf you use this codebase in your work, please cite the following paper:\n\n```tex\n@inproceedings{metametric,\n title={A Unified View of Evaluation Metrics for Structured Prediction},\n author={Yunmo Chen and William Gantt and Tongfei Chen and Aaron Steven White and Benjamin {Van Durme}},\n booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},\n year={2023},\n address={Singapore},\n}\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "A Unified View of Evaluation Metrics for Structured Prediction",
"version": "0.2.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "c5bdcb5ac3313aaa82cb6bcc6cdc0416df744559c45b3bc1639a140d395ee9b9",
"md5": "ea0d11bd83fbe4c0358d368c659c72d5",
"sha256": "26c41dd3b3d6bf17000c60b40e7e3eb340092f34e5327a913c493e6ab69611da"
},
"downloads": -1,
"filename": "metametric-0.2.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ea0d11bd83fbe4c0358d368c659c72d5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 25302,
"upload_time": "2024-11-05T04:53:42",
"upload_time_iso_8601": "2024-11-05T04:53:42.732300Z",
"url": "https://files.pythonhosted.org/packages/c5/bd/cb5ac3313aaa82cb6bcc6cdc0416df744559c45b3bc1639a140d395ee9b9/metametric-0.2.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ed7d54af7e1c4fca7bbfe50ea07c78d0c1f8e1d14dbd5c004f8ce0b17ad8dfda",
"md5": "da000a744490b5ac24f944c5d0000d7c",
"sha256": "76df201ae0e215c5ffbfe4f37bab5bfd9ac0e2b900e6bce4cd4183372c4a17fc"
},
"downloads": -1,
"filename": "metametric-0.2.1.tar.gz",
"has_sig": false,
"md5_digest": "da000a744490b5ac24f944c5d0000d7c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 18675,
"upload_time": "2024-11-05T04:53:43",
"upload_time_iso_8601": "2024-11-05T04:53:43.944836Z",
"url": "https://files.pythonhosted.org/packages/ed/7d/54af7e1c4fca7bbfe50ea07c78d0c1f8e1d14dbd5c004f8ce0b17ad8dfda/metametric-0.2.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-05 04:53:43",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "metametric"
}
