Prof John Kelleher

Background

I received my BSc. in Computing from Dublin City University in 1997, and was awarded a PhD in Artificial Intelligence from Dublin City University in 2003. My PhD research focused on dialog interfaces for situated systems, such as robots, with a particular focus on the interactions between visual attention and language. A number of publications arose from this work, including articles in Artificial Intelligence (https://www.sciencedirect.com/science/article/pii/S0004370205000974) and Computational Linguistics (https://www.mitpressjournals.org/doi/pdfplus/10.1162/coli.06-78-prep14). Following my graduation I completed a number of Post-Doctoral research projects, first working at Media Lab Europe in Dublin and then in the Language Technology lab at the German Centre for Artificial Intelligence (DFKI) in Saarbruecken (https://www.dfki.de/lt/). I returned to Ireland in 2005 to join the School of Computer Science at the Dublin Institute of Technology. Since then I have thought courses in Artificial Intelligence and Machine Learning, and I have been an active researcher in these areas. In 2016 I was awarded the title of Professor by the Dublin Institute of Technology, in recognition of my contributions to research in the institution. In 2016 I was also appointed the Academic Leader of the Information, Communication, and Entertainment (ICE) research institute at DIT. Since 2015 I have been the lead of the ADAPT centre (https://www.adaptcentre.ie) at DIT. In 2018 the European Commission funded the Precise4Q project (https://precise4q.eu), this is a multi-million euro international project focused on improving the clinical treatment of stroke. I will be leading the Precise4Q work package on machine learning and modelling. Deliverables from this project include a number of data driven clinical decision support systems developed using deep learning and other machine learning algorithms and models. 

My core recent interests are at the intersection of machine learning and natural language processing. Examples of recent research, in this space, from my group include word-embeddings and multi-word expressions (Salton et al., 2016), neural language modelling (Mahalunkar and Kelleher, 2018; Salton et al., 2017), automatic image captioning (Lindh et al., 2018), machine translation (Salton et al., 2014), and human-robot interaction (Schutte et al., 2017).  
 
(Lindh et al., 2018) "Generating Diverse and Meaningful Captions: Unsupervised Specificity Optimization for Image Captioning", Annika Lindh, Robert Ross, Abhijit Mahalunkar, Giancarlo Salton, John D. Kelleher. In Proceedings of the 27th International Conference on Artificial Neural Networks (ICANN), 2018.
 
(Mahalunkar and Kelleher, 2018) "Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures", Abhijit Mahalunkar and John D. Kelleher. In Proceedings of the 27th International Conference on Artificial Neural Networks (ICANN), 2018.
 
(Salton et al., 2014) "An Empirical Study of the Impact of Idioms on Phrase Based Statistical Machine Translation of English to Brazilian-Portuguese", Giancarlo Salton, Robert J. Ross, and John D. Kelleher. In Proceedings of the 3rd Workshop on Hybrid Approaches to Translation (HyTra) at the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2014.
 
(Salton et al., 2016) "Idiom Token Classification using Sentential Distributed Semantics", Giancarlo Salton, Robert J. Ross, and John D. Kelleher. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), pages 194-204, (2016).
 
(Salton et al., 2017) "Attentive Language Models", Giancarlo Salton, Robert J. Ross, and John D. Kelleher. In Proceedings of the Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP), pages 441-50, (2017).
 
(Schutte et al., 2017) "Robot perception errors and human resolution strategies in situated human–robot dialogue". Niels Schutte, Brian Mac Namee, John D. Kelleher. Advanced Robotics 31(5), pages 243-257, 2017.
I have published extensively in the areas of artificial intelligence, machine learning, and natural language. I have published 2 books on Data Science and Machine Learning:
 
* Data Science. John D. Kelleher and Brendan Tierney. MIT Press. 2015. (https://mitpress.mit.edu/books/data-science)
* Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies. John D. Kelleher, Brian Mac Namee, and Aoife D'Arcy. MIT Press. 2015. (https://mitpress.mit.edu/books/fundamentals-machine-learning-predictive-data-analyticsdata
 
More details of my publications are available at the following links:
 
Recent invited presentations include:
* "Learning Functions: Understanding Gradient Descent, Backpropagation, and Vanishing Gradients", invited talk at the Open Data Science Conference (ODSC) Europe, London, UK, 2018. (https://odsc.com/london)
* "Machine Learning and Deep Learning in AI", invited Keynote at the 18th International Conference on Artificial Intelligence: Methodology, Systems, Applications (AIMSA), Varna, Bulgaria, 2018. (http://www.aimsaconference.org)
* "An Introduction to Neural Machine Translation", invited Keynote at NDR - The Artificial Intelligence Conference, Iasi, Romania, 2018. (https://www.ndrconf.ai). Video of talk available at: https://www.youtube.com/watch?v=0akSZpcztTo

Best Paper Award at the 9th International Conference on Quality of Multimedia Experience (QoMEX) 2017 for the paper 'A framework for post-stroke quality of life prediction using structured prediction' Andrew Hines and John D. Kelleher. 

  • Email john.d.kelleher@dit.ie
  • Twitter @johndkelleher
  • Teaching Areas

    Artificial Intelligence,

    Machine Learning,

    Data Science,

    Natural Language Processing