SyncAI.news, a Varaisys broadcasting
How Hugging Face Accelerated Development of Witty Works Writing Assistant
HF

Hugging Face Blog

· 1 min read

AI LabsHugging Face Blog

How Hugging Face Accelerated Development of Witty Works Writing Assistant

The Success Story of Witty Works with the Hugging Face Expert Acceleration Program.

If you're interested in building ML solutions faster, visit the Expert Acceleration Program landing page and contact us here!

Business Context

As IT continues to evolve and reshape our world, creating a more diverse and inclusive environment within the industry is imperative. Witty Works was built in 2018 to address this challenge. Starting as a consulting company advising organizations on becoming more diverse, Witty Works first helped them write job ads using inclusive language. To scale this effort, in 2019, they built a web app to assist users in writing inclusive job ads in English, French and German. They enlarged the scope rapidly with a writing assistant working as a browser extension that automatically fixes and explains potential bias in emails, Linkedin posts, job ads, etc. The aim was to offer a solution for internal and external communication that fosters a cultural change by providing micro-learning bites that explain the underlying bias of highlighted words and phrases.


Example of suggestions by the writing assistant

First experiments

Witty Works first chose a basic machine learning approach to build their assistant from scratch. Using transfer learning with pre-trained spaCy models, the assistant was able to:

  • Analyze text and transform words into lemmas,
  • Perform a linguistic analysis,
  • Extract the linguistic features from the text (plural and singular forms, gender), part-of-speech tags (pronouns, verbs, nouns, adjectives, etc.), word dependencies labels, named entity recognition, etc.

By detecting and filtering words according to a specific knowledge base using linguistic features, the assistant could highlight non-inclusive words and suggest alternatives in real-time.

Challenge

Example of context dependent non-inclusive words: 
Fossil fuels are not renewable resources. Vs He is an old fossil
You will have a flexible schedule. Vs You should keep your schedule flexible.

Original source

This story was published by Hugging Face Blog. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on huggingface.co

Similar News