Skip to main content

Explainable Leaderboards for Natural Language Processing

Project description

ExplainaBoard: An Explainable Leaderboard for NLP

License GitHub stars PyPI Code Style Integration Tests

What is ExplainaBoard?

When developing a natural language processing (NLP or AI) system, often one of the hardest things is to understand where your system is working and where it is failing, and deciding what to do next. ExplainaBoard is a tool that inspects your system outputs, identifies what is working and what is not working, and helps inspire you with ideas of where to go next.

It offers a number of different ways with which you can evaluate and understand your systems:

  1. Single-system Analysis: What is a system good or bad at?
  2. Pairwise Analysis: Where is one system better (worse) than another?
  3. Fine-grained Error Analysis: On what examples do errors occur?
  4. Holistic Leaderboards and Benchmarks: Which systems perform best for a particular task?

Using Explainaboard

ExplainaBoard can be used online or offline. For most users, we recommend using the online interface, as it is more interactive and easier to get started.

Online Usage

Browse the web interface, which gives you the ability to browse outputs and evaluate and analyze your own system outputs.

If you would like to evaluate and analyze your own systems programmatically, you can use the ExplainaBoard client.

Offline Usage

For power-users who want to use ExplainaBoard offline, first, follow the installation directions below, then take a look at our CLI examples.

Install Method 1 - Standard Use: Simple installation from PyPI (Python 3 only)

pip install --upgrade pip  # recommending the newest version of pip.
pip install explainaboard
python -m spacy download en_core_web_sm  # if you plan to use the AspectBasedSentimentClassificationProcessor

Install Method 2 - Development: Install from the source and develop locally (Python 3 only)

# Clone current repo
git clone https://github.com/neulab/ExplainaBoard.git
cd ExplainaBoard

# Install the required dependencies and dev dependencies
pip install ."[dev]"
python -m spacy download en_core_web_sm
pre-commit install
  • Testing: To run tests, you can run python -m unittest.
  • Linting and Code Style: This project uses flake8 (linter) and black (formatter). They are enforced in the pre-commit hook and in the CI pipeline.
    • run python -m black . to format code
    • run flake8 to lint code
    • You can also configure your IDE to automatically format and lint the files as you are writing code.

After trying things out in the CLI, you can read how to add new features, tasks, or file formats.

Acknowledgement

ExplainaBoard is developed by Carnegie Mellon University, Inspired Cognition Inc., and other collaborators. If you find it useful in research, you can cite it in papers:

@inproceedings{liu-etal-2021-explainaboard,
    title = "{E}xplaina{B}oard: An Explainable Leaderboard for {NLP}",
    author = "Liu, Pengfei and Fu, Jinlan and Xiao, Yang and Yuan, Weizhe and Chang, Shuaichen and Dai, Junqi and Liu, Yixin and Ye, Zihuiwen and Neubig, Graham",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-demo.34",
    doi = "10.18653/v1/2021.acl-demo.34",
    pages = "280--289",
}

We thanks all authors who shared their system outputs with us: Ikuya Yamada, Stefan Schweter, Colin Raffel, Yang Liu, Li Dong. We also thank Vijay Viswanathan, Yiran Chen, Hiroaki Hayashi for useful discussion and feedback about ExplainaBoard.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

explainaboard-0.12.0.tar.gz (161.7 kB view details)

Uploaded Source

Built Distribution

explainaboard-0.12.0-py2.py3-none-any.whl (260.3 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file explainaboard-0.12.0.tar.gz.

File metadata

  • Download URL: explainaboard-0.12.0.tar.gz
  • Upload date:
  • Size: 161.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.9.15

File hashes

Hashes for explainaboard-0.12.0.tar.gz
Algorithm Hash digest
SHA256 414ec6291e96d3b0d6a45d2565e30a83cc524bfdf531d786cd8da79fa1f20739
MD5 60efcf0bee01278ec36c9b215f056698
BLAKE2b-256 9b5b61cafdcd818144866e8db0188da233a037c0308101790f472ff3eacef334

See more details on using hashes here.

File details

Details for the file explainaboard-0.12.0-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for explainaboard-0.12.0-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 42825b8ad20dba14a1fc53f4a7ae746af3147fafe01b5b2d8e73c1bba0421654
MD5 7e4b41b3515fea4617d61bd2e3473a2d
BLAKE2b-256 df66aa4135a6c50e6042084811a9eb0dfc4bcc6bbc8a3b5caada06a21fcf676e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page