Funded PhD Opportunities 2013
Applications are invited for the PhD research projects listed below. Applicants should hold (or be expecting) a first class or good 2.1 degree in a relevant subject. For project-specific eligibility criteria and funding details please contact the academic responsible for the project before applying; their email addresses are listed below.
To apply, please use the University's online application form at http://www.shef.ac.uk/postgraduate/online and provide the name of the academic (listed below) when asked to name a supervisor.
The following projects have funding:
Neuroeconomics, Reinforcement learning and the equity premium puzzle
Contact Dr Eleni Vasilaki (e.vasilaki@sheffield.ac.uk) or Dr Trevor Cohn (t.cohn@sheffield.ac.uk)
Humans often make decisions based on their desire to maximize profit or reward. Such decisions take place within changing environments, where optimal choices in the past may differ from those in the present. For example, choosing a tracker-rate mortgage might have been at some time in the past a better option than a fixed-rate but today this may have changed. These choices are typically made under uncertain situations and involve a degree of risk. Though the specifics of decision-making mechanisms are still not fully understood, it is evident that fundamentally the human brain is able to identify information sequences that could also correlate with reward.
This project aims to develop a data driven framework for understanding decision-making types of investors, and the key ingredients of making successful investment decisions. We ask the question whether the choices of successful investors have a higher component of sophisticated principles versus the unsuccessful investors, and whether different mixtures of models can account for different investor strategies. We anticipate that the results would be of immediate interest to finance institutions that may want to use our models to extract information about their clients' profiles in order to provide customized financial training or making decisions about investor loans.
Application closing date: 15 May 2013
Computing Veracity of Social Media Healthcare Content
Contact Dr Kalina Bontcheva (K.Bontcheva@dcs.shef.ac.uk)
The aim of this studentship is to design natural language processing methods to compute veracity of social media content and deal with the specifics of medical language. The goal is to model, identify, and verify healthcare-related misinformation and disinformation, as they spread across online media (e.g. patient forums) and social networks. Natural language processing (NLP) now provides many indispensable tools for working with large unstructured text collections, allowing effective search, information extraction and translation. Social media content poses a number of difficult and interesting NLP research challenges. The studentship will also involve a close collaboration with healthcare researchers from a large NHS trust and opportunities for working with natural language processing of clinical records.
The PhD studentship will be associated to a larger research project about developing novel cross-disciplinary social semantic methods, combining document semantics, a priori large-scale world knowledge (e.g. Linked Open Data) and a posteriori knowledge and context from social networks, past user behaviour, and spatio-temporal metadata. The research will also involve use of and further development of GATE (http://gate.ac.uk), which is a leading open-source NLP toolkit, developed by an established team of 12 researchers.
Application closing date: 31 May 2013
Statistical Machine Translation
Contact Dr Lucia Specia (l.specia@sheffield.ac.uk)
The Department of Computer Science invites applications for two PhD studentships in Machine Translation connected to the MODIST project. MODIST (Modelling Discourse in Statistical Translation) is an EPSRC project aimed at modelling discourse level relationships across sentences in statistical machine translation. The studentships will be dedicated to one of the following projects:
• A novel framework for learning valid transitions across machine translated sentences based on rich bilingual linguistic information.
• Novel decoding algorithms that represent expected discourse relationships as document-wide constraints to guide the search for the best translation.
Application closing date: 30 April 2013
Natural Speech Technology
Contact Thomas Hain (t.hain@dcs.shef.ac.uk)
Up to three funded Ph.D. studentships are available in the Speech and Hearing Research Group in the Department of Computer Science, University of Sheffield UK. These studentships are supported by the EPSRC programme grant in Natural Speech Technology (http://www.natural-speech-technology.org/) and associated funding sources. Project topics will be defined within the following areas: techniques for unsupervised learning from continuous streams of speech data; models that adapt to new scenarios and speaking styles; recognisers that can detect "who spoke what, when, and how" in any acoustic environment and for any task domain; PALs – Personal Adaptive Listening systems for people with communication disorders.