Published on Aug, 31 2022 by RGCL.
Our projects and collaborations
At RGCL, we’re always looking for new ways to connect, collaborate, and create with others. As an independent research group and institute, projects have also been our mainstay and a vital part of our research strategy. In this highlight, we take a look at the breadth of projects undertaken at RGCL and RIILP over the past 25 years, as well as some of our ongoing, smaller, and more informal collaborations.
The RGCL project planning whiteboard in our old MB114 office, courtesy of Constantin Orasan
A list of some of our historical RGCL projects, old to new:
CAST: the Computer-Aided Summarisation Tool. The main objective was the research and development of a user-oriented computer-aided summarisation tool. The project also proposed new methods for automatic summarisation and evaluation of automatic summarisation methods. The construction of a corpus with the most important sentences marked and other information useful for summarisation annotated will be an additional product of the project.
BiRD: The goal of this project was to produce a system which will mine information about resources for different research domains on the Internet, and produce a database that will be accessible online for anyone wishing to exploit it. We wrote a recent blog post on it here.
NP4E: a British Academy funded project on development of a methodology in the form of detailed annotation schemes and guidelines for marking noun phrase and event coreference within one document and across different documents.
SYN-CAR: a collaborative project funded by the British Council on coreference and anaphora resolution with University of Tuebingen.
REGEN: Rapid item generation: a project which used NLP technology to speed up the process of building multiple choice questions.
CAID: the development of computer-aided multiple-choice test items. A project which used NLP technology to provide aids to speed up the process of authoring multiple-choice test items.
QALL-ME: an EU-funded project on Question Answering Learning Technologies in a multiLingual and multiModal Environment.
AIR: Automatic Archiving for an Institutional Repository: a JISC-funded project aimed to develop an information extraction system for discovery and extraction of bibliographical data from semi-structured text.
MESSAGE: an EU-funded project which delivered controlled languages standards for messages, alerts and protocols arising from terrorism and other security related risks in order to ensure correct transmission of understanding and reliable translation where necessary.
FIRST: an FP7-funded project which deployed and developed language technology to automatically detect and remove obstacles to reading comprehension for people with Autism Spectrum Disorders. See our blog post on it here.
TELL-ME: an EACEA Lifelong Learning-funded project which aimed to teach vocationally-specific languages to healthcare professionals and help them to communicate at work. See our recent blog post on it here.
DVC: AHRC-funded project which aimed to discover characteristic patterns of use for English verbs and show how meanings are associated with patterns of word use, rather than words in isolation. We wrote an in-depth blog post on it here.
EXPERT: EXPERT (EXPloiting Empirical appRoaches to Translation) aims to train young researchers, namely Early Stage Researchers (ESRs) and Experienced Researchers (ERs), to promote the research, development and use of hybrid language translation technologies. The overall objective of EXPERT is to provide innovative research and training in the field of Translation memory and Machine Translation Technologies to 15 Marie Curie Fellows. We published a recent blog post on it here.
PALinkA: a long-term internal project which develops a multipurpose annotation tool, e.g. for coreference resolution.
MARS: Mitkov’s Anaphora Resolution System. A long-term internal project which develops a knowledge-poor anaphora resolution for English.
NBME: the National Board of Medical Examiners. We have had an ongoing and long-term collaboration with this US organisation since 2005. Read more about it here.
As well as these larger and more formal projects, we also have continuous conversations and ongoing collaborations with our internal and local partners. See, for example, our collaborations made thus far in the Responsible Digital Humanities Lab, established just last year in 2021.
Dr Richard Evans compiled data from collaborations involving RGCL members in the 1995-2016 period:
Since 2016, RGCL has changed considerably and many more recent collaborations have occurred. However, as one can see from the graph above, RGCL is a research group that has always been very much open to collaborating with the research community!
We regularly receive enquiries from external, industry-based professionals on potential collaborations, such as those of Translution and NBME, as well as newer and budding collaborations with e.g. NHS medical staff looking to utilise Machine Learning in their day-to-day test result processing.
If you have an idea for a collaboration with RGCL, get in touch!