The Language and Computation group is an interdisciplinary group that was established in 2001 as a focus for work at the intersection of language analysis and computational techniques. It fosters interaction between researchers within the University, and includes staff and students from the School of Computer Science and Electronic Engineering, the Department of Language and Linguistics, and the UK Data Archive.
The research by the members of the Language and Computation group has covered most areas of Computational Linguistics and Natural Language Engineering.
- Grammars and Parsing: research focuses on Constraint-Based grammars formalisms and statistical and symbolic parsing.
- Semantics and semantic interpretation: our research in this area includes work on the formal semantics of language, and its logical foundations (Fox), on psychologically motivated computational models of semantic processing, on vector-based models of lexical and text representation, used, e.g., in anaphora resolution.
- Applications: some of the areas of interest include generation, e.g., for dynamic web page generation, information retrieval and web search, machine translation, dialogue systems.
Current and Past Projects
- ESRC Large Centre, Human Rights, Big Data and Technology (2015-2020). (McGregor, PI. Fox, Kruschwitz, Poesio). The objective of the Centre is to investigate the potential risks and advantages offered by Big Data technology in the context of Human Rights.
- Using NLP to Support the Generation of Human Rights Violations Reports (2014-2017). (Poesio/Fox (PI), Alhelbawi, Kruschwitz). A KTP Project with Minority Rights Group (MRG). The objective of the project is to use NLP methods to collect, classify and filter reports of human rights violations reported via social media or SMS to support the reporting activities of MRG.
- SENSEI (2013-2016). (http://www.sensei-conversation.eu/) (Poesio (PI), Kabadjov, Kruschwitz). A EU project on using discourse analysis tools in support of the summarization of conversations – both spoken and online. As part of the project we co-organized the 2015 MULTILING Shared Task on Summarizing Online Forums (http://multiling.iit.demokritos.gr/pages/view/1531/task-onforums-data-and-information)
- Automatic Adaptation of Knowledge Structures for Assisted Information Seeking (AutoAdapt EP/F035357/1), a project involving the Department of Computing and Electronic Systems, Robert Gordon University Aberdeen and the Open University (EP/F035705/1). This project aims to develop and evaluate methods for adapting automatically constructed domain models to the population of users’ search or browsing behaviour. Application and large-scale evaluation of the developed methods in two information seeking scenarios – namely, interactive search and browsing – will be performed on a number of domains.
- Development of an Intelligent mail server, a project involving the Department of Computing and Electronic Systems and Active Web Solutions (AWS), an Ipswich based company devoted to cutting edge enterprise information systems.
- Creating anaphorically annotated resources through semantic wikis (AnaWiki) (EPSRC)
- Learning Disabilities Data and Information Infrastructure Project (ESRC)
- Markup-Based Knowledge Extraction Project (EPSRC)
- Anaphora Resolution and Underspecification (EPSRC)
- Mondaq KTP 2: company name detection and industry sector identification (KTP project)