This page lists a small number of my publications. For a more complete list, head over to Google Scholar.


  • V. Tablan, K. Bontcheva, I. Roberts, and H. Cunningham. Mímir: An open-source semantic search framework for interactive information seeking and discovery. Journal of Web Semantics: Science, Services and Agents on the World Wide Web, 2014. (doi:10.1016/j.websem.2014.10.002 | Preprint PDF)

This paper describes GATE Mímir - a system for semantic indexing and searching over large collections of annotated documents.


  • V. Tablan, I. Roberts, H. Cunningham, and K. Bontcheva. a Platform for Large-Scale, Open-Source Text Processing on the Cloud. Philosophical Transactions of the Royal Society A, 371(1983), 2013 doi:10.1098/rsta.2012.0071. (Open Access)

In this paper we describe the design and architectural choices behind the service. This is an extended version of the paper we presented at the e-Science UK All Hands Meeting 2011, for which we received the best paper award.

  • H. Cunningham, V. Tablan, A. Roberts, K. Bontcheva. Getting More Out of Biomedical Documents with GATE's Full Lifecycle Open Source Text Analytics. PLoS Comput Biol 9(2): e1002854. doi:10.1371/journal.pcbi.1002854 (Open Access)

This paper starts with an updated description of the tools in the GATE family, including more recent additions such as GATE Mímir. The second part of the paper is focused on using GATE for biomedical research.


  • V. Tablan. Toward Portable Information Extraction. Ph.D. thesis, Department of Computer Science, University of Sheffield, Sheffield, England. (PDF)

This is my PhD thesis which focuses on methodology for repeatable results when performing Information Extraction in different applications. It includes a fairly in-depth description of JAPE and of the first version of the GATE ML layer (now superseeded by a different implementation).


  • cite title="A Natural Language Query Interface to Structured Information">V. Tablan, D. Damljanovic, and K. Bontcheva. A Natural Language Query Interface to Structured Information. In Proceedings of the 5th European Semantic Web Conference (ESWC 2008). Tenerife, Spain. (PDF)

This paper presents the early work we did on interrogating knowledge bases with natural language queries. My co-author Danica Damljanovic carried this research further and developed it into the FREyA system, as part of her PhD.


  • V. Tablan, T. Polajnar, H. Cunningham, and K. Bontcheva. User-friendly ontology authoring using a controlled language. In 5th Language Resources and Evaluation Conference (LREC). Genoa, Italy. (PDF)

This paper presents our experiments with producing and enriching knowledge bases through the use of a controlled language.


  • M. Dowman, V. Tablan, H. Cunningham, and B. Popov. Web-Assisted Annotation, Semantic Indexing and Search of Television and Radio News. In the 14th International World Wide Web Conference. (PDF)

This paper presents the work we did on semantic annotations of multi-media material (BBC broadcasts in thiws case). Our approach relies on multi-source information extraction followed by cross-validation of results.


  • K. Bontcheva, V. Tablan, D. Maynard, and H. Cunningham. Evolving GATE to Meet New Challenges in Language Engineering. Natural Language Engineering, 10. (PDF)

This paper surveys the the new functionality in GATE added since the version 2.0 release in 2002. That was the first release of the second generation of GATE software, this time implemented in Java.


  • V. Tablan, C. Ursu, K. Bontcheva, H. Cunningham, D. Maynard, O. Hamza, et al. A Unicode-based Environment for Creation and Use of Language Resources. In 3rd Language Resources and Evaluation Conference. (PDF)

In this paper we describe the Unicode support provided by the first Java-based GATE release (GATE version 2.0).