caterinabi/nlp-for-spoken-corpora

Personal project I am working on to create a corpus of interactions in spoken French for syntactic and prosodic investigations.

A little bit about me 👀

👩‍🎓 Former postdoctoral researcher at the University of Cambridge, UK, now Data Scientist at Five9.

📚 Interested in linguistics, data, all sorts of NLP-powered technologies, and conversation design.

🧑‍🦽 Hoping to make a difference by creating a more accessible and safer world for everyone through technology.

🤖 Founder and Lead NLP Engineer at the Omdena Cambridge local chapter, where we develop applications to fight misinformation and promote diversity and inclusion in technology 🔥

📭 You can reach out to me on and/or check out my up-to-date CV in this repo 😎

What I've been up to lately 🙃

🤖 As a part of my training in ML, I have been developing a Recommendation Ranking System along the lines of that of Facebook Marketplace.

🚀 My colleagues Giuseppe Samo, Fuzhen Si and I have been playing with the 🤗 Transformers to understand bias in Healthcare Communication (one paper has been published, one submitted, and one is on its way).

👀 I have recently collaborated on the Deploying a Classifier to Stop Online Violence Against Children using NLP and Conversational AI Chatbot for People Affected by Inflation Omdena Local Chapters, and I'm now leading several tasks (data collection, EDA, data pre-processing) of the Building a Chatbot for Tourists in the UAE using NLP and Detecting Hateful and Offensive Language using NLP Chapters 🔥

🤓 I am working on pypelet](https://github.com/CaterinaBi/pypelette), a community project that utilises NLP to create an open source corpus of spoken interactions in the Romance languages 🔥 (join us! ♥)

Technologies that keep me up at night 🤦‍♀️

Languages and tools

My statistics 🏅

If you wish to support my training, hit the button below!