Making sense of the growing literature requires methods that will increase the speed and reliability of knowledge discovery. Moreover, due to proliferation of scientific databases and ontologies, discovery of previously unknown knowledge demands that scientists engage with many resources, covering different levels and views of (multiple) domain space in context (e.g., degree of confidence in a finding). This constitutes a major challenge in applications arising from the high complexity of mechanisms whose detailed description can only be derived from analysis of heterogeneous sources. Natural Language Processing plays a key role in automated semantic metadata extraction, driving the extraction of structured information from unstructured documents in the form of named entities, and the fine-grained and often complex relations between them (events).
Increasingly, it has become important not only to extract complex relations but also to capture their contextual interpretation such as degree of confidence, or certainty in a finding.
Sophia will describe NLP methods for the extraction of structured representations from text for downstream applications while addressing challenges of information extraction tasks.
Zoom link: https://uqz.zoom.us/j/83209084379
Speaker
Sophia is a Professor of Computer Science at The University of Manchester. Her main areas of research are Natural Language Processing and Text Mining applied in Biomedicine. She is the Director of the UK National Centre for Text Mining, Deputy Director of the Institute of Data Science and AI (Manchester), Turing Fellow, ELLIS member, and Distinguished research fellow at the AI research centre (AIST Japan). Her research contributions are in information extraction, scientific discourse analysis, emotion detection, computational terminology, for applications such as systematic reviews, semantic search, knowledge graph construction, pathway/database curation in domains such as systems biology, cancer, public health, biodiversity, and history.
Venue
Hawken Building (50)