I am an aficionado of Natural Language Processing (NLP), with strong focus on Information Extraction, Finite-state Technology, and the development of efficient Text Mining tools that REALLY WORK !

Specific Interests

    Information extraction: named-entity recognition and normalisation, name matching, event extraction, multilingual domain-adaptive information extraction techniques
    Finite-state technology: finite-state automata and transducers, finite-state based grammar formalisms, compression techniques, pattern matching
    Open source intelligence: security-related online news surveillance and social media mining
    Natural Language Engineering: general-purpose text processing architectures, shallow grammar formalisms, large-scale NLP
    Data Science: machine learning (supervised, semi-supervised and unsupervised), shallow and deep learning, text classification and clustering, feature engineering, data normalisation
    Other: knowledge discovery, information retrieval, question answering, information management and sharing


    jakub >ad< piskorski >dot< waw >dot< pl