NLP people @ York
Suresh Manandhar is a lecturer in the Department of Computer Science. He is generally interested in a wide range of topics related to natural language processing. These span grammar formalisms, constraint logics, constraint solving, machine learning, learning of lexical relations, question answering systems, minimally supervised learning of syntax, semantics and morphology.
Ioannis is a Research Associate in the Department of Computer Science working on the INDECT project. INDECT is a 5 year research project funded under the EU FP7 IP programme.He is interested in a variety of topics related to statistical Natural Language Processing (NLP), i.e. stochastic, probabilistic and statistical methods that deal with several NLP problems including word sense disambiguation, word sense induction, term recognition & keyword extraction, collocation extraction and others.
Siva Reddy is a PhD student working on Compositional Distributional Semantics. Any distributional model that aims to describe the language adequately needs to address the issue of compositionality. Compositionality deals with composing the semantics of text sequences from the semantics of smaller entities like words or phrases. Many functions have been proposed to perform semantic composition. Until now Siva has explored different ways of representing the meaning which suit well for semantic composition. Siva has proposed a Dynamic Prototype Vector based representation of meaning which is found to have achieved state-of-art results in Semantic composition.
Shuguang Li is a PhD student in Department of Computer Science. He has both academic and commercial experiences in natural language processing. He has a broad interest in Natural Language Processing spanning machine learning, question-answering systems, dialogue systems, English spelling and grammar checking.
Burcu Can is a PhD student in Department of Computer Science. Her research field combines a series of machine learning methods with unsupervised learning of morphology and syntax. She is using statistical learning methods including Bayesian modeling and non-parametric Bayesian modeling to analyze the morphological structures in languages by combining with syntactic information. She explores ways to combine these learning mechanisms within either a sequential process, or a simultaneous process where syntax and morphology are learned cooperatively."