Natural Language Processing Research Group

Natural Language Processing Research Group established in 1993. Is among the biggest and many effective language processing groups within the United kingdom and it has a powerful global status.

Natural Language Processing (NLP) is definitely an interdisciplinary area that utilizes computational techniques:

To research the qualities of written human language and also to model the cognitive systems underlying the understanding and manufacture of written language (scientific focus)

To build up novel practical programs including the intelligent processing of written human language by computer (engineering focus)

The group’s research interests fall under the broad regions of:

Information Access. Building programs to enhance use of information in massive text collections, like the web, newswires and also the scientific literature. Subtopics include: information extraction, text mining and semantic annotation, question responding to, summarization.

Language Assets and Architectures for NLP: Supplying assets — both data and processing assets — for development and research in NLP. Includes platforms for developing and implementing real life language processing programs, most particularly GATE. the overall Architecture for Text Engineering.

Machine Translation. Building programs to translate instantly between human languages, permitting accessibility huge quantity of information designed in languages and simpler communication between loudspeakers of various languages.

Human-Computer Dialogue Systems. Building systems to permit spoken language interaction with computer systems or embodied conversational agents, with programs in places for example keyboard-free use of information, games and entertainment, articifial buddies.

Recognition of Reuse and Anomaly. Looking into approaches for identifying when texts or servings of texts happen to be used again or where servings of text don’t match surrounding text. They have programs in places for example plagiarism and authorship recognition as well as in discovery of hidden content.

Foundational Subjects. Developing programs with human-like abilities for processing language requires progress in foundational subjects in language processing. Regions of interest include: word sense disambiguation, semantics of your time and occasions.

The NLP group’s studies have received support from: the EU’s Framework Programmes (Frameworks 4,5, 6 and seven), the United kingdom research local authorities — the EPSRC, BBSRC, MRC and AHRC — as well as other industrial sponsors, including GlaxoSmithKline and IBM.

The NLP group has close associations using the Speech and Hearing and knowledge Retrieval research groups which execute research into other parts of computational processing of human language.