Recently, Tridion’s partner Coreon GmbH convened with Tridion’s team to discuss and understand the way in which Coreon’s multilingual knowledge systems deliver value to increasing number of global enterprises.
We had Jochen Hummel, co-founder and CEO of Coreon, lead the presentation. Jochen is also the CEO of ES Team, Vice Chair at LT Innovate, and was the former CEO at Trados.
Introducing Coreon – Uniquely connects language with conceptual knowledge
Jochen briefly introduced Coreon as a Berlin-based software company, serving as a leader in Multilingual Knowledge Systems with SaaS offering.
The software makes search, machine learning, and IoT applications interoperable. It enables multilingual AI and is deployed across industry, eGov, and education sectors. It is hosted on German data centers.
Coreon complements Tridion, at the heart of Coreon is the unique fusion of terminology with taxonomy / thesaurus / ontology. Coreon’s tool marries language with knowledge in a holistic way. It addresses the gap or black hole that currently exists between terminology and taxonomy (knowledge graphs).
Coreon deploys specialists in both these areas, these specialists have collaborated and built a unique solution. It helps multilingual knowledge workers, content creators, and experts to unlock value across various business processes such as search, text mining, IoT, classification, and conversational AI.
Jochen touched upon the importance of structured data and knowledge graphs, both an integral part of Tridion’s solution, to turn information into knowledge. Coreon comes into Tridion to combine multilingual terminology list with knowledge map which results in multilingual knowledge system.
EuroVoc Case Example
Coreon has done it before at a large scale and is an ideal solution to bring into Tridion. Jochen shared the case study of EuroVoc, a database that EU uses to classify all the information. The knowledge graph is created only once, then the linguists label it and recycle it in different languages which can be delivered across different countries.
For Advanced Linguistic Search, Jochen recommends converting key search strings into meaning, which means locating and connecting these in the taxonomy. It can be done by first creating domain heat maps in the system and then linking it to other datasets (DMS, ERP, HR, etc.). This ensures that search strings don’t get lost in silos, but reach to the correct information in the system.
All of this is performed through Coreon Multilingual Classifier tool whether its website or documents and thus goes with both Tridion Sites and Tridion Docs:
Business Benefits
Jochen mentioned a few examples such as customers finding relevant products on ecommerce platforms leading to higher sales irrespective of the language being used to perform the search. Other example is a global machine manufacturing enterprise that runs business processes around the world in different languages, it benefited from greater efficiency and thereby cost savings.
In the government sector, eGov benefits from seamless and accurate information exchange across different countries in different languages, which leads to greater efficiency.
Brand communication is effective only when it two-way and multilingual
Jochen emphasized that most of the enterprises around the world primarily focus on effectively communicating information to their clients. But miss the point that today it’s increasingly a two-way process. Customers are communicating through product search, chat box, comments, blogs, reviews, social media posts, etc., which are spread inside and outside the enterprise systems.
It is therefore critical to understand what customers are communicating and when customers do communicate they prefer to use the language that they are most comfortable with. This means the enterprises need to be equipped with multilingual tool to be able to capture their customers’ feedback.
Obviously, this is not possible manually and hence Coreon offers multilingual AI based tools such as chat bots, text analytics, and competitive intelligence. AI learns with data and half of this data is in the text form.
A comprehensive knowledge translation engine
Jochen explained the entire process in which the content creation and translation works using the knowledge of subject matter experts. The content is created in a form that is consumable by machines.
Coreon has built a process which it terms as ‘Knowledge Factory’, which has various stages or modules that ensure that language translation is accurate and optimized for quality. It involves use of checks and balances on AI.
Jochen compared and contrasted content translation with content creation to explain the way both work is not too different. Further he also listed the ways in which content differ based on their degree of expressiveness.
Coreon’s differentiation
Jochen, using a 2×2 matrix explained that while there are many solutions in the market that excel in either linguistic strength and multilingual coverage or semantic expressiveness / machine-readiness, but not at both. Coreon with its multilingual AI for humans and machines coupled with strong translation processing capabilities that excels at both!
Further, Jochen explained that many a times there are customers that have even 100,000 concepts involved to process in a chat GPT and hence taxonomization is complex even with AI. In such scenarios he depicted an approach that Coreon has adopted. It involves building clusters that combine similar concepts (related to each other) into one bucket. These clusters have sub-clusters beneath them again combining similar but lower-level concepts.
This requires machine learning and humans to work together to arrive at such classification. And this is where combined Tridion and Trados can make content in any language to connect to such classification in English.
Multilingual knowledge system (MKS) use cases
Working with the content created by combined Tridion and Trados solution, MKS can facilitate seamless two-way communication between customers and enterprises. For example, Jochen mentioned that if a customer sends a query in a local language (not English) then traditionally it will first need to be converted to English for the customer support representative to be able to understand. And then then customer support’s response in English will need to be converted back to the local language for the customer to understand.
This is where MKS comes into the picture and send the customer’s query to the classification system, finds a response in the local language, and communicates it as is to the customer. Combined with Tridion and Trados, MKS works as a single source of truth. It covers content translation / creation, term annotation / classification, semantic search, synchronization / interoperability, conflict resolution, natural language generation, and AI customization / tuning / correction.
In-house multilingual AI solution at RWS
RWS with combined Trados and Tridion has localization under one / single solution. It is able to seamlessly process both content creation and content translation under one roof and thus deliver multilingual AI.
About the Author
Wali Naderi is Product Marketing Manager at RWS.
About RWS
RWS is the global leader in content management and translation technology and services. 90 of the top 100 global companies work with RWS. Tridion Docs provides streamlined end-to-end component content management. It includes easy web-based authoring, reviewing, versioning, translation, and publication management, underpinned by the DITA XML standard. As a true collaborative environment with a familiar Microsoft Word-style interface, subject matter experts (SMEs) in your organization can contribute their knowledge.
Authors and reviewers can work simultaneously in the same document providing comments to each other, tracking and merging changes. Tridion Docs supports global enterprise use cases including single sourcing, product documentation, learning and training, policies and procedures, and efficient translations with delivery to multiple end points such as documents, PDFs, knowledge portals, Intranet, customer facing websites, apps, chatbots, and IoT devices.
Contact RWS here or visit their website at rws.com. Twitter:@rwsgroup, Linkedin: RWSGroup.
