Every day we write some text. We try to write grammatically correctly and politely where we have spelling and grammar checkers to support us. But many people struggle to ensure that their writing does not contain deterring words. 
Research shows [1] that the use of non-inclusive language (especially gendered, ageism, and racist words) has a particularly strong impact on missing a large share of potential talents in the labor market. 

The smart tool Witty can assist in automatically detecting and suggesting alternatives to deterring language, enabling inclusive writing. 
Witty is a browser plugin that makes inclusive writing possible at any given time for anyone. It is suitable for newsletters, social media, communication in general, and job advertisements. 

The Witty Works startup was created about nine month ago and currently has 11 people in the team, of which five are from the engineering group. 
The core algorithm is based on Natural Language Processing (NLP) advanced technologies. We combine modern transformer architecture and rules-based approach. We created our own glossaries (German and English) with inclusive and non-inclusive words with the help of our highly trained language specialist, and based on studies and research in that field.
We use ​​NLP pre-trained models for German and English correspondingly (SpaCy) to transform the words in the text into dictionary-like forms (which are called ""lemmas""), perform linguistic analysis, and extract the linguistic features from the text. In this step, we also do named entity recognitions to extract geographic location, organization's name, people, numbers from the user text if needed. After that, we search through our inclusive and non-inclusive dictionaries if any of the words or idioms from the user's text belong to them or not. In this step, we highlight the words related to non-inclusive language, propose the alternatives, and explain why this word is non-inclusive. We also highlight inclusive words to show and encourage people to use them more often.
Currently, we are implementing the transformers (BERT, Hugging Face) in order to identify properly the right meaning of the words, as well as to classify the job related text and to perform the sentiment analysis of the text. 

In order to summarize. Our tool Witty helps detect and reduce bias in the text and assist people in writing more diversely and inclusively with the help of Natural Language Processing.
 [1] Iris Bohnet, What Works: Gender Equality by Design, Harvard University Press, 2016