Our TAS Tagger solution specializes in tagging (labeling) documents (articles) and providing convenient handling of these tags.
In the user interface, tags and their relations, such as synonyms, co-occurrences, or broader and narrower terms can be configured. This solution increases the efficiency of the document tagging process. And this is extremely important when it is about tagging the articles of a significant participant of the publishing market.
How? The following use case illustrates this.
Our client, one of the leading media companies in Hungary required a maintenance system to make the tagging procedure of their articles more effective and more convenient. We developed the given solution so that journalists obtain automated support for the article tagging.
The development was based on three important customer requirements:
1. auto-tagging of articles in the archive, to make previous contents easier to search and find
2. helping journalists in getting tag suggestions to choose from after writing an article
3. built-in user management with multi-level permission system
Would you like to learn more about our text analytics solutions? Write us or send a message using the contact form at the bottom of this page.
TAS Tagger UI (Note: these are sample data and not actual tags of a live system)
Tags can be named entities like persons, locations and organizations, or also key phrases or even Machine Learning based tags.
There are several ways to manage the extracted tags. You can create a relationship between them, organize them in groups, or even create a stop list.
the following relations can be created between tags:
– synonyms, eg. Football – Soccer
– co-occurrences, eg. Anfield – Liverpool
– narrower and broader terms, eg. Motorcycles – Vehicles
The connections appear at the tag suggestions to the journalists, or in automated mode it can be configured to set all the synonyms as tags for example.
You can create categories to group your tags. For example tags related to Sales can be added to the certain category.
Stoplist can be set in the form of regular expressions for the tags. If the article contains this expression then the tag won’t be suggested. For example you can set that if an article contains ‘rain check’ then the tag ‘weather’ won’t appear.
It is possible to search amongst the tags. Users can search based on character matching or filter the list by status and categories.
Graph view helps the user to analyze the connection chain between tags.
Graph view in the Tagger UI
A multilevel permission system has been set up so tasks can only be done by users who has appropriate rights to do them.
Reader: Readers can only browse between the tags, but they can’t edit anything
Editors: They can manage the tags
Admin: They are allowed to manage both of the tags and the categories
Admins can manage the tags and also the tag categories
These permissions can be set in the Manage Users menu.
What is the duration of implementing a TAS Tagger solution? – Every TAS tagging project has different requirements, it could be realized even in 15-30 days. A Machine Learning-based tagging solution needs more time, especially if you don’t have annotated data yet.
Can you handle special requirements? – Sure, no problem. We are not only the owners of TAS Platform solutions – but also a software development enterprise so we are capable to develop your custom solution.
Are you prepared to get into business with enterprises outside of Hungary? – We have several partners in Europe and we also have overseas customers. We all do speak in English, and some of us in German.
Do you have other questions about the product or the quotation? Send your message.