The European Language Grid has published its book ‘European Language Grid - A Language Technology Platform for Multilingual Europe’ on the results of the project for European language technology and NLP cloud platform. This book documents the evolution and results of the EU project European Language Grid (2019-2022) and describes the architecture and implementation of the ELG Language Technology and NLP cloud platform. Readers are introduced to the ELG community consisting of hundreds of industrial and academic stakeholders all over Europe. This book is open-access, which means that you have ..read more

We are proud to announce that the European Language Grid (ELG) selected EDIA's 'CEFR Labelling and Assessment Services' project proposal to receive financial support. With 103 project proposals, the competition was tough. Ultimately, the ELG Pilot Board picked five projects (amounting to € 584,396), and EDIA was among them. A total of eleven projects focus on contributing resources, services, tools, or data sets to the European Language Grid platform to increase its coverage. Four projects are developing applications using language resources and technologies available in the ELG platform. The ..read more

With the educational content shift taking place, publishers need to innovate. In a previous blog post, we've discussed why embracing content agility is key in this regard. Of course, such transitions require publishers to make investment-related decisions. With every innovation, the main question is, 'Will we make or buy this?' To make: independence + uncertainty Those who decide to develop a new initiative in-house will need to reach into their pockets. R&D, internal development, and maintenance are costly. Such investments do come with an advantage: once you've built your solution, you ..read more

Recently, we've discussed why embracing content agility is key and explained that the road towards it is rather agile in itself. But what to do once you've gone down this road? What is the publisher's next step after digitalisation? Automation tooling: what’s out there? Even though publishers use an increasing number of digital tools (such as content management systems), few have implemented automation — which we believe is a missed opportunity, as it's a logical, beneficial next step. So, let's have a closer look at this form of technological innovation. If you run a spellchecker to make sur ..read more

In our previous blog post, we've discussed the importance of content agility. But how to arrive at agile content? The road towards it is rather agile in itself. Today, we will walk you through the three major stages of an agile process: production, management, and distribution. 1. Production: creating individual content units Authors tend to write books from A to Z. Even if they work on chapters in a non-chronological order, the process is linear — they deliver the book after they've written all pages. When creating agile content, it's crucial to adopt a brand-new perspective. Content agility ..read more

The term 'agile' has become common in software development. Developers used to build their programming schedules around a set-in-stone blueprint. But they increasingly adopt an insights-driven approach, shaping the result as they go. Based on knowledge gained during short iterations, they adjust or change course so as to reach the best possible outcome. With the educational content shift taking place, it's key to embrace the principle of agile when it comes to educational content, too. Let's have a closer look at what we like to call 'content agility.' Accommodating ever-changing needs ..read more

In the past few weeks, we've discussed several types of metadata that benefit from automated labelling: the CEFR, keywords, topic, and learning objectives. Of course, there are many other types of metadata. But the ones we've addressed have a few things in common. It's difficult to use them efficiently, and they're usually not created in an objective, consistent manner. That is why it's so interesting to automate these labels. Not only is automation innovative and impactful, but it also significantly enriches learning materials. Let's do a recap and consider what the futur ..read more

Companies that want to keep up with market developments require well-organised metadata at a very granular level. They need to embrace automated labelling to be ready for the future. But labels and metadata are used at various levels, which means it's not easy to see the forest for the trees. In this blog series, we focus on content metadata. Now that we've discussed the CEFR, keyword extraction, and topic classification, let's have a look at learning objectives tagging. A brief explanation In our view, learning objectives tagging is a form of topic classification. But it has a specific taxon ..read more

To be future-proof, companies need to embrace automated labelling. But where to start? In this blog series, we focus on content metadata. A few weeks ago, we discussed keyword extraction. Today, we'll have a closer look at a related label: topic classification. What is topic classification? Topic classification comes with an aggregated label. The main difference with keyword extraction is that it's broader in nature — once you have a collection of keywords, you can consider the overarching topic. Logically, the term attributed to this label will be a bit more general. Unlike keywords, topics ..read more

Keywords are no science but an art. There is no such thing as 'the right keyword,' as we're talking about a core concept incorporated into a piece of content in the broadest form. Texts don't necessarily need to contain an exact keyword. For example, if the term 'European Union' is used several times, 'European Commission' may be a suitable keyword even though the writer never uses the term. Despite this fluid definition, keywords should be understandable to those who try to find the right ones. That's where automated labelling comes in. Why should you use automated labelling? When teachers a ..read more