University students no longer learn from lectures and books alone. Thanks to the internet, they now have access to a huge range of supporting material, such as lecture notes, assignments, articles, and so on. To organise this material effectively, most universities have invested in a ‘learning management system’ (LMS) to archive and present documents online in a systematic way.
But as the volume of material grows, both students and tutors have the problem of locating the information they need.
“In general it can be hard to find what you are looking for,” says Dr Paola Monachesi of the Institute of Linguistics at Utrecht University. “The normal way to search the LMS is by a full text search. That’s what you do in Google, you just type a word and get a list of results.”
Unfortunately, such searches ignore the relevance and suitability of the ‘learning objects’ they identify. An EU-funded project called LT4eL (Language Technology for eLearning), involving universities in ten European countries, has devised new ways to search by meaning rather than by text.
One approach is to search by metadata – keywords and other labels that tell a potential user much more about a document – but metadata has to be entered manually by the author and the task is often neglected.
“We thought, can we develop a system where keywords are assigned automatically or semi-automatically?” says Monachesi, who coordinates LT4eL.
The project has created a ‘keyword extractor’ that analyses each document in the LMS archive and proposes a list of keywords that the author can accept, reject or modify. The prototype focuses on material in computer science and e-learning and has been designed to work with documents in Bulgarian, Czech, Dutch, English, German, Polish, Portuguese and Romanian.
Trials show that it works faster and more consistently than manual annotation. A related tool even extracts definitions from the material to build a glossary of key terms.
Although online dictionaries are already available, they do have some shortcomings. “Very often the words are ambiguous so you don’t really know the proper definition in the context of your learning object,” Monachesi explains. “’Key’, for example, might mean the key of a keyboard or a key to open a door.” The LT4eL tool ensures that the offered definitions make sense in the context of the course material.
A second, potentially very powerful approach, allows users to search for information by concept. The ‘semantic search’ tool organises keywords and definitions in a hierarchy according to their meaning – an ontology – revealing the relationship between them. For example, a student searching for information about HTML, the language used to mark up web pages, would also be pointed to material about XML, as both are used for similar purposes.
But the real richness of the LT4eL system is that the resources can be cross-referenced between several different languages.
“Since we classify documents through topics we can also search in different languages at the same time,” Monachesi points out. “I had Polish students who could speak English, the course was in English, but they preferred to read documents in Polish. With such a system, I could search in English or Dutch but get Polish documents. So my students could get material in their own language even though I don’t know Polish.”
The system has obvious benefits for students on exchange programmes and those studying a field where much of the material is not available in their native tongue. Because of the choice of languages, the project should help develop ties between ICT research communities in the new Member States and the rest of the EU.
Although the project has been designed with higher education in mind, the tools have been tested with schools in Romania and should also be useful for industrial training.
Tagging the future?
LT4eL was supported by the EU’s Sixth Framework Programme for Research, and the Seventh Framework Programme is funding its successor, LTfLL (Language Technology for Lifelong Learning) which will be further developing the semantic search.
“We see a lot of potential in the semantic search but we noticed that students don’t use it in the way they could,” says Monachesi. “I think this is because it’s new and different from what they are used to on Google, for example.”
So, among other things, the new project will look at the ‘tagging’ system popular on social networking websites like Flickr and YouTube to see if it could be adapted to make the semantic search more user-friendly.
“Maybe we can find a semantic representation more lightweight than our very structured ontology that may be difficult for people to understand.”
For the purpose of the project the LT4eL tools have been integrated into the ILIAS learning management system but Monachesi stresses that the tools are open source and are freely available from the project website and SourceForge.
“This gives the widest possible distribution and dissemination – anybody could use them – but the licence would also allow for commercialisation.”
Christian Nielsen | alfa
Cutting edge research for the industries of tomorrow – DFKI and NICT expand cooperation
21.03.2017 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI
Molecular motor-powered biocomputers
20.03.2017 | Technische Universität Dresden
Astronomers from Bonn and Tautenburg in Thuringia (Germany) used the 100-m radio telescope at Effelsberg to observe several galaxy clusters. At the edges of these large accumulations of dark matter, stellar systems (galaxies), hot gas, and charged particles, they found magnetic fields that are exceptionally ordered over distances of many million light years. This makes them the most extended magnetic fields in the universe known so far.
The results will be published on March 22 in the journal „Astronomy & Astrophysics“.
Galaxy clusters are the largest gravitationally bound structures in the universe. With a typical extent of about 10 million light years, i.e. 100 times the...
Researchers at the Goethe University Frankfurt, together with partners from the University of Tübingen in Germany and Queen Mary University as well as Francis Crick Institute from London (UK) have developed a novel technology to decipher the secret ubiquitin code.
Ubiquitin is a small protein that can be linked to other cellular proteins, thereby controlling and modulating their functions. The attachment occurs in many...
In the eternal search for next generation high-efficiency solar cells and LEDs, scientists at Los Alamos National Laboratory and their partners are creating...
Silicon nanosheets are thin, two-dimensional layers with exceptional optoelectronic properties very similar to those of graphene. Albeit, the nanosheets are less stable. Now researchers at the Technical University of Munich (TUM) have, for the first time ever, produced a composite material combining silicon nanosheets and a polymer that is both UV-resistant and easy to process. This brings the scientists a significant step closer to industrial applications like flexible displays and photosensors.
Silicon nanosheets are thin, two-dimensional layers with exceptional optoelectronic properties very similar to those of graphene. Albeit, the nanosheets are...
Enzymes behave differently in a test tube compared with the molecular scrum of a living cell. Chemists from the University of Basel have now been able to simulate these confined natural conditions in artificial vesicles for the first time. As reported in the academic journal Small, the results are offering better insight into the development of nanoreactors and artificial organelles.
Enzymes behave differently in a test tube compared with the molecular scrum of a living cell. Chemists from the University of Basel have now been able to...
20.03.2017 | Event News
14.03.2017 | Event News
07.03.2017 | Event News
23.03.2017 | Life Sciences
23.03.2017 | Power and Electrical Engineering
23.03.2017 | Earth Sciences