20 April 2012: Sujay Kumar Jauhar, a Master's student at the Research Group of Computational Linguistics at the University of Wolverhampton, has built a system that participated and ranked first in the SemEval-2012 shared task on Lexical Simplification. The system called SimpLex, which was developed jointly with Dr. Lucia Specia, ranked as the best system among nine participants by a statistically significant margin, also outperforming a very strong baseline.
The system uses a linear weighted ranking function composed of three features to produce a ranking. These include a context sensitive n-gram frequency model, a bag-of-words model and a feature composed of simplicity oriented psycholinguistic features. These three features are combined using an SVM ranker that is trained and tuned on the Trial dataset. Further details of the shared task can be found at: http://www.cs.york.ac.uk/semeval-2012/task1/
31 January 2012:
01 January 2012: A new €500,000 project will help medical staff to learn a European language and improve communication with patients.
Academics from the University of Wolverhampton have joined forces with partners from the NHS West Midlands Workforce Deanery and universities and healthcare services in Spain and Germany for the TELL-ME project.
The initiative will provide self-study material for English, Spanish and German which uses vocabulary specifically aimed at medics.
The two-year project was developed in response to a European Union priority to increase people’s mobility around Europe, and the European Parliament is also discussing ways to enhance cross-border healthcare. With all the benefits of this mobility, it is important to maintain high quality medical treatment and ensure a high standard of doctor-patient communication.
Professor Ruslan Mitkov, Director of the Research Institute of Information and Language Processing (RIILP) at the University of Wolverhampton, said: “A breakdown in patient-medic communication can lead to aggravated health problems and increased healthcare costs, so it is critically important to minimise language barriers wherever possible.
“By focusing on three of the most spoken languages in Europe our project will help not only English, German and Spanish native speakers working in their home countries, but also medical professionals from countries such as Poland, Sweden or Bulgaria who wish to work in another EU country. In addition, it can have an influence outside the EU as citizens improving their English or Spanish skills could work in North and South America and Oceania, and non-EU patients visiting the EU are likely to be able to use one of these languages.”
Funding for the project has come from the Leonardo da Vinci Multilateral Projects for Development of Innovation, which is part of the European Commission’s Lifelong Learning Programme.
The University of Wolverhampton is co-ordinating the project with partners from NHS West Midlands Workforce Deanery; Universidad de Málaga, Spain; Universität des Saarlandes, Germany; Hospital Pascual, Spain and Universitätsmedizin Mannheim, Germany.
The package involves a range of products including work-related language exercises, self-assessment tools and an interactive dictionary of key vocabulary and concepts. These will be tested out on trainees by the medical partners and disseminated to key national medical policy makers.
The languages targeted by the project - English, Spanish and German - are among the five most spoken languages in Europe.
with the support of the Lifelong Learning Programme of the European Union
23 December 2011: The Research Group in Computational Linguistics will be closed for Christmas from 12.30 on Friday 23 December 2011 until 09.00 on Tuesday 3 January 2012. We would like to wish all our colleagues, students and collaborators past and present a very Merry Christmas and a Happy New Year!
25 November 2011: Congratulations to Georgiana Marsic, who successfully defended her PhD thesis on "Temporal Processing and its impact on Question Answering" at a viva voce examination earlier today.
04 November 2011:
Professor Ruslan Mitkov has been conferred the Honorary Degree of Doctor Hon Causa by the University of Plovdiv for his outstanding contribution to research and applications of research to society.
Professor Mitkov, who is the Director of Research Institute in Information and Language Processing at Wolverhampton, was chosen to receive the honour as he is leading expert in his field and hails from the town of Plovdiv originally, although he has never studied at the university.
He said: “This was a great honour for me. For me it was a special and unique experience to be awarded this honorary degree by the university of the town where I was born and to see so many people from my home country and all over the world show their respect and appreciation for what I do.
“The ceremony itself was on the day of the 50th year anniversary of Plovdiv university, and was a very emotional and unforgettable event. I would like to thank the University of Wolverhampton for its unreserved support since I joined in 1995. This support has been instrumental in my achievements in research so far.”
01 October 2011:
The Research Group in Computational Linguistics is co-ordinating a €2 million project, funded by theEuropean Commission FP7 ICT Call 7, which officially starts today.
The FIRST project (A Flexible Interactive Reading Support Tool) will run until September 2014. Its objective implement, deploy, and evaluate technology to support the authoring of accessible content for users with Autistic Spectrum Disorders (ASD). These are neurodevelopmental disorders characterised by qualitative impairment in communication and stereotyped repetitive behaviour. People with ASD have deficits in comprehension of speech and writing including misinterpretation of literal meanings and difficulty understanding complex instructions. They are confused by idioms, figures of speech, abstractions, uncommon words and lack of precision.
Prof. Ruslan Mitkov, Director of RIILP, said: "Given the very stiff competition in the current economic climate, it is a tremendous achievement for the University of Wolverhampton to be awarded this funding. I am delighted that we are being given the opportunity to develop language technology which will help people with Autism Spectrum Disorders to access all the opportunities that Europe has to offer. This highlights the importance of research which is immediately relevant to and benefits society, as opposed to “blue-sky” research which may take some years to have an impact."
The project is expected to make an impact on the quality of life of autistic people, improving their access to educational, vocational, cultural, and social opportunities in Europe.
19 September 2011: The Research Group in Computational Linguistics recently co-organised the very successful RANLP 2011 conference with the Linguistic Modeling Department of the Bulgarian Academy of Sciences (involved mainly with on-site organisation). Programme Chair Prof. Ruslan Mitkov and PC Coordinators from our side Irina Temnikova and Natalia Konstantinova, assisted by other members of RGCL, were involved with the running of both the main conference and the Student Workshop. The conference involved participants of 44 different countries. The scientific programme of the main conference (to the composition of which RGCL greatly contributed) was received with approval by the conference participants, who rated the conference as highly successful.
The next RANLP conference will take place in 2013 in Hissar, Bulgaria.
16 June 2011: Five members of the Research Institute of Information and Language Processing took part in Cancer Research's Race for Life on Wednesday 15 June and raised an outstanding £570 for the charity. Regulars Alison Carminke, Natalia Ponomareva and Yvonne Skalban were joined by first-timers Miranda Chong and Lucia Specia in the 5km run around West Park. All managed to complete the race in under 33 minutes, with the fastest member of the group, Natalia Ponomareva, completing in just 25 minutes. The runners would like to thank all their sponsors, many of whom were from within the University, for their generous donations to Cancer Research.
08 June 2011: Dr. Lucia Specia has been awarded the prize for best paper at the 15th Annual Conference of the European Association for Machine Translation for her paper "Exploiting Objective Annotations for Minimising Translation Post-editing Effort".
22 April 2011: The University of Wolverhampton is closed for Easter from Friday 22 April to Tuesday 26 April inclusive.
20 April 2011: Natalia Konstantinova and Yvonne Skalban participated in the 1st round of the Vitae Midlands Hub poster competition, held at the Wolverhampton Arena Theatre. They were both awarded a prize of £100 and their winning posters are among five that will be put forward to the grand final on 11 July 2011.
24 December 2010: The University of Wolverhampton is closed for the Christmas break from 15.00 on Friday 24 December 2010 until 09.00 on Tuesday 4 January 2011. We wish all our colleagues, collaborative partners and students a very Merry Christmas and a Happy New Year.
19 November 2010: Miguel Angel Rios Gaona's thesis ("Word Sense Disambiguation and recognizing Textual Entailment with Statistical Methods") was awarded second place for Best MSc thesis in Artificial Intelligence in the 2010 national competition of PhD theses in Artificial Intelligence organized by the Mexican Society for Artificial Intelligence (SMIA).
11 October 2010: We invite applications for a two year Erasmus Mundus MA course on NLP and HLT,
organized jointly by Universite de Franche-Comte (France), Universitat
Autònoma de Barcelona (Spain), Universidade do Algarve (Portugal) and
the University of Wolverhampton (UK). Alternatively, you can register for a one year masters in Language and Information Processing run by University of Wolverhampton. read more
13 September 2010: We would like to welcome the new Masters students who arrived in
Wolverhampton at the start of September. The students will complete one year of a two year Erasmus Mundus course; International Masters in Natural Language Processing and Human Language Technology run by the Research Institute in Information and Language Processing. The course is made up of international students who spend portions of the two years study at any of the four consortium universities involved in the running of the Erasmus Mundus Masters programme. As students in their first and second year of study arrive in Wolverhampton we would like to welcome
them and invite them to immerse themselves in the vibrant life at
Wolverhampton University and to attend all of the lectures and talks
available to them at the Research Institute in Information and Language
Processing. A full course induction will run on Tuesday 14 September in
MC232. The materials can be viewed online at this address.
01 July 2010: 
17 June 2010: Alison Carminke, Natalia Ponomareva and Yvonne Skalban have raised a total of £236.64 by participating in Race for Life
09 May 2010: The systems developed by Lucia Specia and Wilker Aziz were ranked second and fourth (out of 14 participants) at the SEMEVAL's Cross Lingual Lexical Substitution competition. The systems are based on dictionaries automatically extracted from parallel corpora using mutual information, statistical machine translation and online learning.
07 May 2010: Lucia Specia's thesis ("A Relational Approach for Word Sense Disambiguation") was awarded the Best PhD Thesis prize in a contest organized by the Propor Conference. The contest considered theses addressing some aspect of the Portuguese language and defended in the three years preceding the conference.
04 May 2010: Bob Foster also put forward a poster for the 1st round - local competition of the Vitae Midlands Hub poster competition. His poster also won a cash prize of £100 and will join Miranda's among the five posters put forward from the University to the grand final at Nottingham in July. Bob's poster included details from a paper that was published at RANLP 2009 and three papers that have been accepted for ICALT 2010 and ICEIS 2010.
03 May 2010: Miranda Chong participated in the 1st round - local competition of the Vitae Midlands Hub poster competition, held at the Wolverhampton Arena Theatre. Her winning poster was amongst one of other fives that will be put forward to the grand final, being awarded a cash prize of £100, with an additional £20 awarded for the best “Clarity of Message”
17 November 2009: Erasmus Mundus Masters Course - International Masters in NLP and HLT: CALL FOR APPLICATIONS students and scholars
16 October 2009: The proceedings and presentations from the eETTS workshop are now available online.
06 August 2009: The system developed by Iustin Dornescu was ranked first for the second year in a row at the GikiCLEF competition. Iustin competed against 16 other systems and his overall score was almost double that of the second place competitor. Iustin's system processed questions with geographical constraints in ten languages and for nine out of ten languages he obtained the best results. More information can be found here. The Research Group in Computational Linguistics would like to congratulate Iustin on his excellent performance.
09 July 2009: Congratulations to Dr Constantin Orasan and Iustin Dornescu, who have recently been ranked second and third in the GREC Named Entity Generation Challenge 2009 for their two systems for generation of referential expression in the ACL shared task.
26 June 2009:
Natalia Ponomareva, one of the research fellows in the Research Institute in Information and Language Processing, was recently given the prestigious award of 'Best Paper' at a top European Conference.
The Programme Committee of the 14th International Conference on Applications of Natural Language to Information Systems NLDB 2009 at Saarbruecken, Germany, commended Natalia with the 'Reind Van De Riet Memorial Award' for the best paper in the Main Conference for the contribution:
AIR: A Semi-Automatic System for Archiving Institutional Repositories by Natalia Ponomareva, Jose Manuel Gomez and Viktor Pekar
01 June 2009: The Research Group of Computational Linguistics is currently a co-organiser of the international conference RANLP-2009, which is ranked as the third best Natural Language Processing conference in the world. For further information, please e-mail the organisers.
02 April 2009: RANLP Workshop on Natural Language Processing methods and Corpora in Translation, Lexicography, and Language Learning organised by members of research group
18 February 2009: The NP4E corpus is also available in MMAX format.
23 December 2008: RAE 2008 results: the Research Group in Computational Linguistics is one of the top performers in UK Linguistics research
22 December 2008: PhD Studentship in Interactive Question Answering
14 December 2008: The video of the second QALL-ME demo is available on YouTube
19 October 2008: CALL FOR APPLICATIONS: Erasmus Mundus Masters Course International Masters in NLP and HLT
26 June 2008: New job vacancy: Lecturer/Senior Lecturer or Reader in Natural Language Processing. Closing date: 4th August 2008
07 April 2008: The term-based summarisation demos developed in the CAST project are back online.
04 March 2008: New job vacancy: Research Fellow or Senior Research Fellow in Computer-aided Multiple-Choice Test Item Development. Closing date: 28 March 2008
20 February 2008: The research group is expanding. You can find some members of the group in MB114. Please check the contact us page for details.
15 November 2007: Mphil Studentship in Natural Language Processing (GBP 18,000 for 18 months)
29 October 2007: New job vacancy: Research fellow on AIR. Closing date: 30 Nov 2007.
01 October 2007: The JISC-funded project "Automated Archiving for an Institutional Repository" (AIR) which aims to develop an information extraction system allowing for speedy discovery and extraction of bibliographical data from semi-structured text has started.
13 August 2007: The list of accepted papers at the Computer Aided Language Processing workshop is available.
03 August 2007: We are currently migrating our server, so certain pages are currently not working. We do apologize for any inconvenience this may cause to you.
04 May 2007: System developed by PhD student performs best at international competition
31 January 2007: The training data for the Anaphora Resolution Exercise (ARE) is available.
23 November 2006: New Postdoctoral Research/Senior Research Fellowship in QALL-ME project
02 November 2006: Preliminary announcement of the 1st Anaphora Resolution Exercise (ARE)
02 October 2006: The QALL-ME project has started
22 September 2006: The research group has participated in the WiQA competition at CLEF2006.
06 September 2006: Three new jobs available at the Research Group in Computational Linguistics (1 Professor, 2 Research Fellows)
03 May 2006: New job available: (Senior) Research fellow on computer-aided multiple-choice test items development.
11 October 2005: The Research Group in Computational Lingustics has moved to new offices. Please check the contacts webpage
31 March 2005: The stand-alone version of the term-based summariser has been released.
03 August 2004: Article about the Research Group in Computational Linguistics published by Gabriela González in Argentina.
01 April 2004: New British Academy funded project on Annotation of cross-document coreference has started.
17 March 2004: New demo which retrieves words which are most similar to a particular *sense* of the
target word.
30 October 2003: The program of presentations is available online.
01 October 2003: Georgiana Puscasu has joined the Research Group in Computational Linguistics as a PhD student working on coreference resolution and temporal processing for Question Answering.
17 June 2003: RESEARCH STUDENTSHIP IN QUESTION ANSWERING (£7,500 a year). The University of Wolverhampton, School of Humanities, Languages and Social Sciences invites applications for a four-year-funded research studentship in Computational Linguistics. The successful candidate is expected to develop a question answering system for English which employs coreference resolution and temporal reasoning.
16 June 2003: The new website was made accessible.
02 June 2003: Our demos are back online.
31 May 2003: Some of our demos do not work because of some problems with one of our servers. IT is investigating this problem. We hope to solve the problems soon.
29 May 2003: A new demo by Viktor Pekar was added. This program implements several the distributional similarity measures allowing to extract the top 30 most similar nouns to a noun introduced by a user. The program implements 10 similarity measures.
28 May 2003: The new web page will be ready soon. It will contain lots of enhancements and nice stuff. It is made using the latest technologies eg. PHP, MySQL.