Concept Tagging
Benefit from highly customizable and precise automated tagging and classification
Semantic concept tags, or semantic metadata, are information building blocks that help classify information assets, making them easier to find, use, and link to each other. Many organizations have their own methods of tagging (classify) their content; however, these are typically manual. Manually tagging entire databases or content management systems (CMS), file by file, is very time consuming and involves a lot of people.
Why you should replace manual tagging with concept tagging.
Use case
Manual Tagging
Concept Tagging
Use Case:
Streamline customer support by replacing manual tagging in inbound categorisation with auto tagging.
- TIME SAVING
Manual Tagging
SEC
Concept Tagging
SEC
Use Case:
More detailed tagging improves findability and reduces time spent on search.
- AVG. NUMBER OF TAGS PER DOCUMENT
Manual Tagging
Tags
Concept Tagging
Tags
Use Case:
Controlled vocabularies ensure consistent and typo-free tagging of documents.
- REDUCTION OF WRONG TAGGING
Manual Tagging
%
Concept Tagging
%
Concept tagging – door opener to intelligent content
The concept tagging method which is built off semantic concept tags enables organizations to better structure their databases and CMS as well as build intelligent search engines and robust recommender systems.
Precise search and recommendations
Usability
Integrability
PoolParty already has out-of-the-box integrations with widely used platforms like SharePoint, Adobe Experience Manager, and Tridion Docs. Thanks to its rich API, it is highly integrable with any enterprise content or data management system. With PoolParty Semantic Suite, you can transform your workflow without making any major changes to your existing systems.
Automated creation of concepts
PoolParty has introduced the Taxonomy Advisor, our large lanaguage model (LLM)-based suggestion tool that streamlines the process of creating concepts. The Taxonomy Advisor promises the following:
- Adding concepts: Users can select and edit from suggested narrower and related concepts
- Generated concept definitions: Users can add/edit auto-generated definitions that are suggested by the Advisor
- Streamlined editing: Users can add suggestions in bulk operations or singularly, depending on their preference
- Reliable recommendations: The LLM is connected to company documents and data so that the suggestions are domain specific and not random
- Less time researching: The user still has the ability to refine or reject the Taxonomy Advisor’s suggestions, but spends less time having to outline new terms from scratch
Useful Resources
Learning hub:
Read our in-depth guide about concept tagging and auto classification.
Semantic Booster for AEM
Read about our tagging solution for Adobe Experience Manager.
Smart Tagging for Tridion
Read about how our tagging integration with RWS’ Tridion.
Graphwise for M365
Read about our solution for Microsoft 365, now powered by Graphwise.
Frequently reported challenges for organizations using manual text tags.
Error-prone data
A common result of manual tagging is inconsistent search results. Even with clear guidelines, people end up developing their own way of assigning metadata and create inconsistencies. Therefore, manual tagging without controlled vocabularies is not scalable and doesn’t work for organizations that store large quantities of files.
Quality of tags decreases over time
Not fit for AI
Simple text-based tagging is arguably a thing of the past, since it cannot keep up with the high volumes of content organizations use. Modern search-, insight- and recommendation engines need contecxt and intent to fuel their alogorithms. Only concept tagging can return results based on a much more diverse profile of attributes.
In order to solve these problems, organizations can implement an auto classification solution that is driven by semantic technology using concept tagging. This methodology scans the contents of a document and automatically assigns concept-based tags that can be indexed into the appropriate categories and classes.
When an auto classification strategy is driven by simple text-based tags, the search engine can only retrieve information based on the exact terminology. Therefore, every word that the user enters in a search field should be extremely precise and relevant. On an ecommerce site, if a user wants to buy a blue cardigan, they would have to enter “blue cardigan” into the search field. The advantage to concept tagging is that users can enter unspecific language or multiple keywords, and the search engine could retrieve the precise results that they want. For example, if the same user wants to buy a cardigan but can’t remember the name “cardigan,” entering “blue sweater” in the search field can still retrieve results for a cardigan because sweater and cardigan are bundled together in one concept.
On the left side of the screenshot, these concepts are organized into a hierarchical taxonomy which gives structure to the documents and their tags – fulfilling the final step of auto classification. The concepts 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. The benefit to maintaining tags in a taxonomy is the consistency it provides through its hierarchical structure and controlled vocabularies.
Knowledge Graphs make the difference
The added benefit to combining auto classification with knowledge graphs is that you can map the logic between tags. Visually represented in a web of sorts, knowledge graphs link together various business assets, entities, concepts, etc. together to see how these things are related. They help to provide context to all these little pieces of information because they allow you to see how they all fit together.
Semantic tags that are mapped in a knowledge graph identify relationships between concepts, terms, documents, etc. and the contents within those documents. With semantic tags, you can bundle these relationships together by adding labels of synonymous terms that make search platforms function smarter. When the semantic metadata is stored in a knowledge graph, documents can be indexed and queried better, allowing for precise user 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.
Even more, concept tagging serves as a fundamental step to making graph-based recommender engines. Semantic graph-based recommender systems are the powerful alternative to standard search for their ability to suggest smarter results based on the user’s interactions with a platform and understanding of context and meaning.
Gartner says: “Active metadata is artificial intelligence-enabled and includes capabilities to coordinate analysis in multiple data management tools and even engage in dynamically altering their operations at the highest maturity level. Importantly, advanced passive metadata concepts such as automated metadata collection and updates are not active metadata.”
Gartner Inc, : ‘Gartner Critical Capabilities for Metadata Management Solutions’ (Mark Beyer, et al, November 2020)
If a research team for a pharmaceutical company is trying to write a paper on heart-related conditions. If the user searches for “heart rate,” they will only be given results that explicitly talk about heart rate. With a graph-based recommender system, the user gets the obvious results as well as intelligent “further reading” suggestions. I.e. you type in the words “heart rate” and get documents also relating to heart diseases, abnormalities, etc. relating to heart rate; in this case, the recommender system understands that one thing affects the other. Altogether, the content creation process is much easier and helpful.
The metadata from the semantic concept tags helps the user become better oriented to their CMS so they can use it more efficiently.