Arturas joined the Office for National Statistics (ONS) as an economist after finishing his bachelors in Economics and has worked in several areas across the organisation. Throughout his work he built data processing pipelines, fostered the development of python programming capability and eventually moved on to a Data Science role where he worked with distributed computing pipelines.
Arturas joined the campus in May and has been working on a natural language processing pipeline. He is interested in applying natural language processing, computer vision and general machine learning to solve practical problems.
Many datasets contain variables that consist of short free-text descriptions of items or products. This technical report describes how we developed and implemented a natural language processing (NLP) pipeline that produces a well structured and hierarchical dataset.
Read more