Today, we are excited to be launching the Harmony Question Parsing (Token Classification) Challenge in support of the Harmony project, which aims to develop a tool to help researchers make better use of existing data by harmonising questionnaire items and measures across different studies—potentially in different languages—through an approach based on natural language processing (NLP).
Harmony is a collaboration between researchers at Ulster University, University College London, the Universidade Federal de Santa Maria and Fast Data Science. The Harmony project has been funded by Wellcome as part of the Wellcome Data Prize in Mental Health and by the Economic and Social Research Council (ESRC).
The challenge is to develop an improved algorithm for identifying mental health survey questions and selectable answers in plain text, which in practice typically comes from scanned PDFs. This work has the potential to drastically save time for psychology researchers working in the field. This competition will last approximately two months and finish on 28th March at 5pm (GMT).
This competition will have the following prizes as Amazon (UK) vouchers:
- First place: £1,000
- Second place: £500
If you are interested in taking part, join the conversation on the Harmony Discord and the DOXA AI Discord servers.
For more information on the challenge and the dataset, check out the DOXA AI competition page.