Adding value to NLP: a little semantics goes a long way.
Abstract: Natural language processing technology is now ubiquitous, even if there are still many challenges to be faced in its development. From sentiment analysis to machine translation to chatbots; from medical systems to online shopping to fake news; even if not visibly apparent, NLP tools are now lurking hidden in the depths of an enormous number and range of real-world systems and applications. Techniques have advanced in many directions in the last 20 years thanks primarily to developments in machine learning and deep learning technologies, and to the concomitant creation of and attention to language resources. In this talk, I shall examine the role of semantics in NLP applications. It is perhaps surprising that despite recent advances in Semantic Web technology and NLP, researchers and practitioners in domains ranging from journalism to rocket science have yet to grasp their potential, and are still manually grappling feral spreadsheets and databases. I shall discuss how NLP infused with even small amounts of semantics can be a drastic game-changer in fields as diverse as crisis communication, politics, journalism, medicine, literature, and history, using examples from some of our recent projects and applications.
Bio: Dr Diana Maynard is a Senior Researcher at the University of Sheffield, where since 2000 she has been one of the key developers of GATE, leading work on Sheffield’s open-source multilingual text analysis tools. Her main research interests are in developing tools and applications for information extraction, sentiment analysis, social media analysis and terminology, and investigating correlations between human behaviour and language. She has led teams on numerous European and national projects in a wide range of fields including politics, climate change, natural disasters, human rights, geography, journalism, and scientometrics. She regularly provides consultancy and training on text and social media analysis in both the public and private sector, as well as widespread community engagement through talks, tutorials, and publications.