https://github.com/mateibejan1/ad-nlp

Benchmark for Anomaly Detection in Natural Language Processing
https://github.com/mateibejan1/ad-nlp

Last synced: about 1 month ago
JSON representation

Benchmark for Anomaly Detection in Natural Language Processing

• Host: GitHub
• URL: https://github.com/mateibejan1/ad-nlp
• Owner: mateibejan1
• License: gpl-3.0
• Created: 2022-06-16T09:04:28.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-08-29T10:39:08.000Z (over 1 year ago)
• Last Synced: 2023-08-29T11:35:37.372Z (over 1 year ago)
• Language: Python
• Size: 1.75 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AD-NLP

 A Benchmark for Anomaly Detection in Natural Language Processing

 

To reproduce our experiments, you must clone the repository, download the data and then run the provided Python scripts, as explained below.

 

To download the preprocessed data, run the `download_data.sh` script. It will pull the data from Google Drive and unzip it in the current directory. Althernatively, you can download the data manually at the following links: 

* We will provide the links to the datasets after the anonimity period for the conference ends.

To redo our experiments, you must download the data and then run the following Python scripts:

1. `run_baselines.py`, which trains and tests both OCSVM and Isolation Forest.

2. `run_cvdd.py`, which trains and tests CVDD.

3. `some_script.py`, to be added by Andrei.