Skip to content

John Snow Labs LangTest 1.1.0: Enhancing Support for different toxicity tests, templatic augmentations, BBQ-data, HF dataset support for summarization, CSV augmentations for text classification and new robustness tests.

Choose a tag to compare

@ArshaanNazir ArshaanNazir released this 18 Jul 19:09
· 3244 commits to main since this release
c656960

πŸ“’ Overview

LangTest 1.1.0 πŸš€ comes with brand new features, including: new capabilities to run different types of toxicity tests (lgbtqphobia, ideology, racism, xenophobia, sexism), support for doing templatic augmentations, extending support for HF datasets for summarization, support for BBQ-data, custom-replacement dicts for representation tests, CSV augmentations for text classification, using poetry as a dependency manager and adding new robustness tests (adjective-swapping and strip-all-punctuation) with many other enhancements and bug fixes!

A big thank you to our early-stage community for their contributions, feedback, questions, and feature requests πŸŽ‰

Make sure to give the project a star right here ⭐


πŸ”₯ New Features & Enhancements

  • Adding support for improved toxicity tests #628
  • Adding support for templatic augmentations #629
  • Adding support for strip_all_punctuation test #618
  • Adding support for adjective-swap tests #611
  • Adding support for custom replacement dictionaries for representation and bias tests #600
  • Adding support for BBQ-data #609
  • Adding support for CSV augmentations in text classification task #617
  • Adding support for hf datasets for summarization #589
  • Adding poetry as a dependency manager #588
  • Adding support for listing all available tests #592
  • Adding support for enabling user to only install the backend libraries needed #597

πŸ› Bug Fixes

  • Model hub handler #601
  • Fixing augmentations for swap-entities #622
  • add_contraction bug for QA/Sum #615

❓ How to Use

Get started now! πŸ‘‡

pip install langtest[transformers]

Create your test harness in 3 lines of code πŸ§ͺ

# Import and create a Harness object
from langtest import Harness

h = Harness(task='ner', model='dslim/bert-base-NER', hub='huggingface')

# Generate test cases, run them and view a report
h.generate().run().report()

πŸ“– Documentation


❀️ Community support

  • Slack For live discussion with the LangTest community, join the #langtest channel
  • GitHub For bug reports, feature requests, and contributions
  • Discussions To engage with other community members, share ideas, and show off how you use NLP Test!

We would love to have you join the mission πŸ‘‰ open an issue, a PR, or give us some feedback on features you'd like to see! πŸ™Œ


♻️ Changelog

What's Changed

Full Changelog: 1.0.0...1.1.0