Tagmatic was originally designed to meet the challenges of automatic content tagging in the publishing industry, and is ideally suited to classification and tagging of news, sport and entertainment content.
Most large publishers need to tag or classify their content for a number of reasons :
Typically tagging is a manual task, integrated into the editorial workflow and the CMS. Increasingly, publishers are working to automate this process using NLP and machine learning techniques.
Automating content tagging unlocks a lot more value, as the automated-tagging system can be used to
For this reasons, publishers are investing large sums and time in building their own automated tagging systems. However what may seem like a simple problem in the R&D labs can turn into a much more complex and expensive problem, when put into production.
Tagmatic is an AI and Machine Learning fully managed SaaS platform. We built Tagmatic to make it as simple as possible to integrate automated tagging into your publishing systems, addressing all the key challenges :
Building you own AI based tagging solution is no mean feat. It is not just a data science problem, but involves software engineering, testers, DevOps, infrastructure, scaling automation, model deployment automation, continuous machine learning model training automation, as well as the project management and business processes that accompany a project of this nature. Both the total cost of ownership and time-to-deliver is substantial.
With Tagmatic you can be up and running in hours, not months, at a fraction of the total cost and you can put your data scientists to work on your market differentiating data outomes instead.
Contact us now for a free trial.
Data Language have great experience in information architecture for broadcasters, which is quite rare. Their enthusiasm has rubbed off on my team, which is a real bonus.
Tagmatic is a commercial SaaS platform for sophisticated, language agnostic text classification using AI and machine learning. It is a fully managed cloud service, that classifies text content against your own dictionaries, taxonomies, vocabularies or knowledge graph entities. It is based on pure machine-leaning algorithms and thus avoids problems such as disambiguation, and it evolves its models as your content evolves.
Tagmatic is language and character set agnostic. It works out-of-the-box on all latin character set languages, as well as cyrilic, greek, arabic, and any other alphabet based language. It has not yet been deployed on Chinese and Japanese Kanji, but if you have a project for classification of Kanji text, we would be happy to work with you.
Tagmatic is incredibly easy to integrate. It has two simple webservice endpoints. One for train, one for predict. Documents are sent to the train endpoint for on-the-fly training, where Tagmatic seemlessly and silenty recomputes, optimises, and redeploys its machine learning models. Documents are sent to the predict endpoint to get a sub-second classification response. We also have a visual playground that can be used for experimenting, and trialling the service. All the infrastructure is managed by us, you can be up and running in just hours.
Tagmatic is pure machine learning AI. It learns on-the-fly as you feed it tagged content, and then can tag fresh or un-classified content from what is has learnt. As such it learns not just the terms to tag with, but also the style of tagging. It does not suffer from disambiguation problems, as it knows the difference between turkey and Turkey because you do.
Technically Tagmatic trains a set of machine learning models automatically as you send it content, self-tunes and optimises these models, and updates them on-the-fly so it continually improves and evolves as your content evolves.