His most recent work includes the automated production of part of a statistical publication on teacher mobility, the first time this has been done in Government. He is also a lead on the cross-Government Social Media Research Group, which has published guidance on social media analysis and recently, in conjunction with Microsoft, run a cross-Government hackathon using social media data.
Our judges will be assessing the applications over south korea rcs data the next few weeks, so send your application in as soon as possible. We’ll announce the Data Impact Fellows in mid – September.
We hired James, a recent graduate, for a summer project to develop a chatbot to try and solve a closed domain question answering (QA) problem, using the domain of ‘research data management’. James highlights the main steps and some of the challenges that arose.
“The basic premise of a QA chatbot is to map a question to a relevant answer. ways from machine learning to more statistical approaches such as cosine similarity (which still have an element of machine learning to learn the initial vectors). In other words, one can draw similarities between question and answering with information retrieval. What follows is my experience of chatbot development.”