Engineering Doctorate (EngD) Studentship in Large Scale Complex IT Systems: The Development of an Adaptive and Intuitive Information Retrieval System - FULLY FUNDED

Applications are invited for a Research Engineer to work on a research project in the development of an adaptive and intuitive information retrieval system. The project is supervised and sponsored by Purple Frog Text. The research project is fully funded and will be carried out in conjunction with studying for an Engineering Doctorate (EngD) in Large Scale Complex IT Systems (LSCITS) at the University of York.
.
Purple Frog Text
Purple Frog Text (PFT) was established after winning an innovation grant from the UK government on the basis of more than 20 years research in the fields of information retrieval, information & knowledge management and artificial intelligence.

Purple Frog's leading edge technology provides a powerful platform for organisations to manage rapidly increasing and continuously changing corporate information, and enabling them to organise and harvest all relevant information, regardless of origin and format. This information is transformed by user into high-value knowledge which can then be shared and applied to task and project completion.

Research project

The main objective of this project is to develop and implement an innovative bottom-up design of an adaptive and intuitive information retrieval system as part of Purple Frog’s new generation enterprise knowledge management system. This ‘tailor-made’ system will be able to identify the information needs and many other relevant characteristics of each individual user together with extracting contextual domain specific information. The result will dramatically increase the accuracy and efficiency of the system.

Some of the challenges involved in this project are as follows:
• Identifying concepts and their relationships in the context of the given query (concept search)
• Identifying entities and their possible relationships in the context of the given query (entity extraction)
• Extracting phrases from the given contents that are suitable and relevant to the given query (pattern recognition)
• Dynamic multi-faceted search- utilising relevant concepts and entities dynamically to provide a taxonomy of the search results and the filtering mechanism
• Extracting contextual information, tacit knowledge/information
o User’s information needs
o User profile
o User’s expertise
o User’s behaviour
o Domain specific information
• Obtaining and developing domain specific dictionary from the contents (including n-grams)
• Query expansion by utilising such additional information
• tuning the overall system to the user’s needs
• Efficient and optimised scoring and term weighting rendering a more efficient and effective ranking mechanism
• Multi-language capability
• Ability to access and extract all the necessary patterns and entities from a large volume of multi-formatted and noisy environment
• Machine learning techniques: the ability to learn from these sources and suitably fine Limited hardware and resources with the demand for real time and high performance computing (large scale computing)
o Suitable response time
o Fast indexing process
o Adaptive and elastic cloud computing
• An overall design: a new generation single platform multi-functional enterprise knowledge management system including search, collaboration, collaborative e-discovery, information organisation, visualisation and fully user tailor-made