Danushka Bollegala

Department of Computer Science,
The University of Liverpool.

RM 224, Ashton Building, Ashton Street, Liverpool, L69 3BX, UK.
Phone: +44-1517954283
Mail: danushka (dot) bollegala (atmark) liverpool.ac.uk
Google Map

I am Danushka Bollegala, Professor in Natural Language Processing at the Department of Computer Science, The University of Liverpool, United Kingdom. See my short vita.

I lead the Data Mining and Machine Learning (DMML) Research Group and the Natural Language Processing Group. I am also a member of the Institute for Risk and Uncertainty of the University of Liverpool, and Global Research Center for Big Data Mathematics National Institute of Informatics (NII), and a full-member of the Engineering and Physical Science Research Council's (EPSRC) Peer Review College. I hold visiting fellowships at School of Informatics at University of Sussex and National Institute of Informatics. I am an Amazon Scholar and a senior fellow at Cookpad.

My research interests are Artificial Intelligence, Natural Language Processing and Machine Learning. I am particularly interested in how the meaning of words and sentences used by humans can be represented in a format that could be understood by machines such as computers or robots. This subfield of AI is called natural language processing (NLP).
I have worked in a wide-range of problems in NLP see here and my publications. I teach Data Mining and Visualisation (COMP 527), a masters-level module taught at the University of Liverpool. Details about my current/past students/post-docs are here. I have experience in industrial collaborations in the form of startups, knowledge transfer partnerships and consultancies. If you are interested in collaborations please contact.


  • We are hiring NLP scientists at Amazon, Berlin!
  • Tree-Structured Neural Topic Model accepted to ACL-2020.
  • Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction accepted to LREC-2020.
  • Do not let the history haunt you: Mitigating Compounding Errors in Conversational Question Answering accepted to LREC-2020.
  • Meta-Embedding as Auxiliary Task Regularization accepted to EACI-2020.

Books written by me