21 June 2012
Unsupervised learning in Natural Language Processing
Meeting Room 10, 2nd Floor, JLB
12:30pm - 13:45pm
Dr Suresh Manandhar - University of York
Unsupervised learning is an emerging area within NLP that poses interesting and challenging problems. The primary advantage of unsupervised and minimally supervised methods is that annotated data is not required or required only in small quantities. In this talk, I will present our current work on word sense induction, morphology learning and compositional distributional semantics. Sense induction is the task of discovering all the senses of a given word from raw unannotated data. Our collocational graph based method achieves high evaluation scores while overcoming some of the limitations of existing methods. Furthermore, senses can be grouped into a hierarchy by inferring random trees over graphs. In a similar vein, we show that hierarchical morphological paradigms can be learnt from unlabelled data within a Dirichlet process based learning framework. Finally, within the emerging area of compositional distributional semantics we show how sense information can be exploited in computing compositional vectors.
Suresh Manandhar is currently a lecturer in Computer Science at the University of York. He completed his PhD in 1994 from the University of Edinburgh. He has a wide range of interests in natural language processing. He has published over 100 papers in a range of topics that include - constraint logics for NLP, stochastic constraint programming, Inductive logic programming, grammar engineering, unsupervised learning of morphology, grammars and semantics, question answering systems, persuasive dialogue systems etc. His current interests are in unsupervised learning of natural language.
Save to your Calendar