Public Funding for Linguamatics Limited

In the age of Big Data, knowledge workers - individuals, companies and organisations whose primary focus is knowledge and information extraction and usage - find it increasingly difficult to search for and identify accurate and relevant information. In the domain of scientific literature and IP search, where the underlying corpora are growing at a huge rate, this is a daunting task and human expertise and involvement remain critical. This project aims to develop a suite of tools that will enable users to search for and identify relevant information within a corpus more efficiently and effectively. The methods developed will deploy new search paradigms together with semantic-based analysis, domain and lexical linguistic ontologies in order to understand the user needs based on the underlying domain of application and subsequently enable accurate information retrieval through enhanced search and cross-reference of information. The project aims to offer tools for sharing of search strategies which will be identified by observing and understanding patterns in users' search behaviours.

CambridgeIP (CIP) the global innovation and intellectual property consultancy, with the University of Cambridge (UoC) and Royal Society of Chemistry (RSC), propose to develop novel touch interfaces to global scientific literature archives, enabling more intuitive search and analysis across multiple devices. With over 1 billion smartphone users now performing traditionally pc-based activites on their phone, new techniques need to be used for big data analysis. This will be achieved by using the latest advances in touch-screen and mobile interfaces, alongside semantic data analysis. Touch interfaces to the semantic elements will create an intuitive, accessible search platform enabling high level analysis and exploration of highly complex and specialist data sectors. Interactive data analytics and higher level data visualisations will be created to help view patterns within the data. The project will improve specialist and non-specialist access to valuable information from global scientific literature, enhancing R&D, education and entepreneurship.

The current generation of language processing has had considerable success in extracting useful information from large amounts of unstructured text, whether this is research literature or social media. However, adapting to a new domain is often a laborious process, with respect both to diverse types of data (e.g. newswire vs. patent literature) and to the terminology used in a given domain (e.g. in medical practice vs. pharmaceutical research). Humans can perform these tasks on small data sets, but face a challenge in the face of massively increasing amounts of electronic text. The EVOKES project is exploiting distributional similarity techniques to accelerate key components of customisation - the recognition of concepts, and the creation or adaptation of terminologies that link terms to concepts.

Awaiting Public Project Summary

Awaiting Public Summary