It is well known that amount of available unstructured data is growing rapidly. Companies use this data for different purposes, such as detecting trends or extracting valuable pieces of information. However, very few of them have sufficient expertise in the area of “big data” analytics. The main challenge here is to focus research and development activity on applications which are valuable to industry. The “Intelligent Search Systems and Semantic Technologies” laboratory at KFU has substantial experience in the following research fields:
- natural language processing (with focus on Russian);
- scalable solutions for big data text analytics;
- semantic web and Linked Data;
- information retrieval.
We collaborate with ABBYY, Avicomp Services, Leipzig University, Wayne University and Emory University.
Our key projects
- NLP@Cloud (Natural Language Processing at Cloud), a scalable open-source platform for text analytics. The platform is intended for text processing in various subject domains such as social media analysis, information extraction & retrieval, among others.
- Information Extraction system for Russian. The primary goal of the system is to gather mentions of people and organizations, as well as related business events, from online news feeds. The project was started in collaboration with HP Labs Russia.
- iCQA (community question answering, Q&A), a free open-source platform that provides the tools for maintaining and analysis of collaborative Q&A services. It contains a fully-fledged Q&A engine and implementation of state-of-the-art methods and algorithms for mining the data generated by a typical Q&A site.