Select Page

Towards User-Centric Search and an Organized CMS: Semantic AI Integration in RWS’ Tridion.

November 30, 2021

Angela DaSilva

Angela DaSilva

Content Writer


All Blog posts

For most organizations, content management systems (CMS) serve as the backbone of their content maintenance and creation processes. While CMS are inherently crucial, they do not always promise the best experience in terms of being able to organize and search for content. When a CMS is paired with a semantic AI integration, these problems not only dissipate, but also create new opportunities for the user by adding a valuable layer of intelligent user-centric search and personalized recommendations.

The CMS as the “kitchen junk drawer.”

When content is poorly organized or mismanaged, it cannot be found. 

Consider a drawer filled with kitchen “utensils.”  The drawer starts out with cutlery and maybe a gadget or two, and somehow becomes a drawer filled with every odd and end in your house ever. You try to open the drawer, and the ever classic spatula or potato masher prevents you from doing so. At this point, you’ve cluttered up the drawer so much that not only can you not find what you were looking for, you can’t even open it to start.

A digital storage drive or a CMS is not a kitchen drawer, but it does have similarities. Maybe you are a very organized person who has a very organized file system on your personal computer. A company CMS, however, has an inherited “mess.” Over the years of your company’s history, employees – past and present – have uploaded documents, photos, videos, spreadsheets, etc. with different naming conventions (or lack thereof). 

It’s very common to be frustrated in the process of looking for a specific document in a company drive/CMS because you know it exists, but you don’t know what it’s called, where it’s located, or who it was made by. Essentially, you are looking for something with absolutely no clues as to how to find it. In this case, even the most important documents in a CMS can be classified as junk if it’s not labelled or sorted well.

You open the ill-fated “kitchen drawer” to find a specific document to write an article or verify some numbers, and you end up with something different entirely, or not at all. In these cases, you have to very frustratingly produce the article from scratch, when that research document that you were looking for would have reduced your work by a significant percentage.

Bring structure to your CMS to make searching for things easier.

In your company CMS, you can benefit from bringing structure to the inherited mess with tags and taxonomies. To initially organize the CMS, auto classification is the recommended solution. Auto classification serves as an umbrella term for tagging – the practice of extracting and assigning descriptors to your data to create enriched “metadata” – and classification – the practice of categorizing and clustering content. 

Along with extracting tags from documents and data, a successful auto classification strategy requires a strong taxonomy to facilitate the categorization of these tags. Through the use of an entity extractor tool, keywords and labels are extracted from documents that are synced to the taxonomy. These tags can be automatically sorted into their corresponding classes and concept schemes in the taxonomy through predefined rules that have been set up in the thesaurus structure, or refined after manual review. The benefit to maintaining tags in a taxonomy is the consistency it provides through its hierarchical structure and controlled vocabularies.

A controlled vocabulary ensures that your company’s naming conventions remain standardized and consistent, even if different employees or departments across one company use different terminology. By tagging documents using a taxonomy, all this differing terminology can be bundled together in one “concept”. 

How concept tags improve findability and grant user-centric search.

Concept-based metadata increases findability within a CMS because the search mechanisms behind it do not rely on specific keyword input to find things. In other words, descriptors can be bundled together with synonyms and alternative labels so that search will retrieve results based on these synonyms. Term-based tagging can only return results on exact keywords, whereas semantic concept tagging can return results based on a more diverse profile of attributes.

With concept tags and taxonomies, your CMS is already off to a better start. The beauty of semantic technologies is that you can then model relationships of these concepts in a knowledge graph – in doing so, you are giving the tags context and meaning, which your CMS would lack if only operating on its native functionalities. 

When the semantic metadata is stored in a knowledge graph, documents can be indexed and queried better, allowing for precise user-centric search. In a CMS, documents can be tagged with authors, topics, authoring dates, etc. If a user is  looking for a document by one particular author, all those documents tagged with the same author will be retrieved so that the user does not have to sift through the whole database. The user can also locate documents more easily based on their classification, e.g. searching for news items vs. event articles.

Semantic AI integration with RWS’ Tridion breeds better experiences.

When navigability within a CMS is improved, the overall takeaway from using that CMS is a positive one.

An organized CMS and a better, user-centric search is not only coveted, it’s attainable. When semantic AI is integrated with a CMS that is already powerful, positive user experiences are doubled. 

Take PoolParty’s OEM integration with RWS’ Tridion, for example. Tridion is an Intelligent Content Platform that “connects people, processes, and information with the most complete portfolio of collaborative Content Management, Knowledge Management and Headless delivery technologies.” While Tridion has been delivering content management solutions for 25 years, their newly revamped product with PoolParty’s embedded semantics has changed the way that users interact with the system.
RWS pp partner

In other words, PoolParty’s tagging and semantic search capabilities has allowed them to create a unique user experience that provides smarter search and personalized content recommendations. Semantics helps users with the Tridion software not only keep their content organized with rich metadata, it also helps them easily discover their desired content by matching results to their queries with user intent. 

“The ability to match intent to content is the real value of semantic AI,” says Thomas Labarthe President of Language Services and Technology at RWS. “By better understanding customers’ intentions or desires, it immediately guides them to the most appropriate piece of content or information. This open ups fantastic opportunities for brands to deliver a far more intuitive experience on any digital touchpoint – crucial for customer acquisition and retention.”

As RWS’ trusted technology partner, PoolParty Semantic Suite, – more specifically, PoolParty PowerTagging – serves as a foundation to the personalized search experiences Tridion facilitates. PowerTagging hits all the advantages explained earlier in this article – e.g. the organized tags in a taxonomy, the relational modelling between concepts in knowledge graphs – and also helps build semantic search and intent-based recommendations using the context in knowledge graphs. 

This way, the search field in Tridion can make sophisticated matches between the concepts that have been defined in the previous taxonomy and tagging stages. The search does not focus merely on similarities between documents or business objects, but on background and context as well. This behavior widens the scope of what Tridion can recommend, regardless of which specific keywords are entered in the search field.

Read more about our partnership with RWS here >

PoolParty PowerTagging as the opportunity to begin an auto tagging journey.

Tagging with PoolParty is not just about extracting important terms from documents, but linking content to a knowledge graph to give it rich, contextual information. It was designed to be an essential step towards enterprises’ ability to provide personalized recommendations and positive, user-centric experiences. 

PowerTagging does not intend to stand alone; but rather be an integral solution to CMS and content platform providers who are looking to achieve the same experience-oriented goal. PoolParty’s APIs make semantic AI integrations like the one in Tridion possible, whereby existing systems can be enhanced with advanced semantic capabilities in an intuitive way.

When the content management system is already powerful, all that’s missing to deliver personalized recommendations and search is semantic AI. Consider a ready-made semantic AI integration like putting a divider in the kitchen junk drawer; if it improves user experience so drastically with little to no hassle, it’s worth the investment.

Interested in learning more about PoolParty PowerTagging? Check out our integrations page to see the details!


You may also like these blogs …

Taxonomies for Content Management

Taxonomies for Content Management

To find and create content in an organization, having a taxonomy for content management purposes makes all the difference. Read the reasons to implement a taxonomy here.

read more
PoolParty Lifesaver: LLMs and Knowledge Graphs: A Technological Waltz

PoolParty Lifesaver: 5 Hot Data & AI Trends on our Radar

Introducing the PoolParty Lifesaver blog series, bringing you the latest "tech-talk" in an easy-read blog. This blog focuses on upcoming trends in Data and AI including Data Fabric, Semantic Business Layer, Generative Data & Analytics, Graph & Vector Technologies, and Data Literacy.

read more