TAS Tagger

TAS Tagger is a text analytics solution that can extract and define key terms and topics as values from textual content. These terms and named entities (eg, personal names, places, organizations, dates) are identified by computer linguistic and machine learning methods and tools. The applied combination of available methods and tools depends on the needs of the client.

TAS Tagger provides various advantages. Tagging bigger text bodies is improving the usage efficiency of the documents:

• enriching its data (tags are metadata)
• making them more easily searchable (documentations or even emails)
• improving its data quality

In addition, the TAS Tagger solution can provide data for automatic (machine learning based) classification of texts.

Utilizing TAS Tagger does not mean that the company has to give up the systems used so far, it only helps these applications to operate more efficiently, thus elevating the process of gaining insights to a higher level.
However, if the complex user needs necessitate also the implementation of a new search engine within the enterprise IT environment, TAS Enterprise Search is an excellent solution. The parallel application of both solutions puts a real Insight Engine in your hands.

By labeling larger text contents (text bodies), the solution improves the efficiency of using documents (text contents) as labeling enriches the data (the labels are metadata), thereby increasing data quality. With the help of labels, documents or even emails become easier to search. One of the biggest advantages of TAS Tagger is that there is no need to give up the search engine used within the company so far, and our solution nevertheless facilitates its more efficient operation. If the introduction of a new search engine has become necessary in the corporate IT environment due to complex user demands, then the TAS Enterprise search offers an excellent solution, which, together with the knowledge of TAS Tagger, provides a real Insight Engine at your disposal.

To make the right business decisions, it is essential to exploit the potential hidden in a large amount of corporate data. However, it is crucial to recognize and label the details that are important to us in the available company contents. These contents of the corporate data assets can vary widely: business documents (contracts, notes), texts available on the Internet (articles and other documents), scientific contents (essays, dissertations, published research), or even emails.

Whatever means the value for the company in the enterprise data, it is essential to be retrieved and tagged properly, regardless where these values are hidden: in business documents (contracts, notes), texts available on the Internet (articles and other documents), scientific contents (essays, dissertations, published research), or even e-mails.

TAS Tagger is an ultimate tool, providing the combined knowledge of text analytics packages of tech giants as (Microsoft, Google, IBM, OpenAI – ChatGPT) and the advanced solutions of subfield leaders as Babel Street (Rosette Text Analytics), Neticle, Repustate, MeaningCloud.

The TAS Tagger combines the knowledge of integrated modules to deploy the most well-known and widely used text processing methods:

• topic, keyword, and entity extraction
• named entity recognition
• language detection
• sentiment and emotion analysis
• video and audio analysis

All these methods work independently of the specific sector and professional area. The extracted information can be immediately processed with additional systems used by experts from various departments, thus the range of users (analysts, data scientists, managers, HR, sales or marketing specialists) and applications (search engines, BI tools, other solutions already used by the client) is quite extensive.

Beyond this, the TAS Tagger opens new perspectives for both internal and external Data Science teams, as they can create supervised machine learning models in addition to using automatic tags, which can also be utilized within the corporate infrastructure.

With the manual labeling feature (annotation), documents can be prepared for building models. The implementation of these models supports the automatic categorization of textual content.

In addition to the insights gained the required information can be processed immediately with additional systems applied by the different experts of divisions.
These applications may be:

• search engines
• BI tools or
• further market-leading solutions

The best known and most widely applied text processing methods are available:

• topic, keyphrase and entity extraction
• language detection,
• sentiment and emotion analysis
• video and audio analytics

All of these methods operate regardless of the given sector and professional field. Thus the circle of users may also be wide:

• analysts
• data scientists
• researchers
• managers
• HR, sales or marketing experts.

• definition of the text body to be tagged
• specification of tags
• controlling of how precise the tags are
• defining the scope of corporate documents to be labeled
• optionally, collecting textual content available on the World Wide Web beyond corporate data with the help of TAS Data Collector
• defining labels automatically or through manual labeling
• reviewing the obtained labels
• retrieving labels for an arbitrary number of additional documents

TAS Tagger analyses the text body and define tags automatically or the set of possible tags can be defined by the customer in advance. In these cases we build a professional tag-database in partnership with the user. This database contains the pre-defined tags. The machine learning model uses this database and could be re-trained every time the tag-database changes. This re-training method can be accomplished by the user through the TAS user interface. The tagging process is also trackable on the same GUI. Once a tag is accepted, the software stores it. The system also stores the previously tagged text contents.IDOL (Intelligent Data Operating Layer) is Micro Focus’s comprehensive analytics solution, the integration of which enables video and audio analytics, so tags can already be assigned to visual and audio content.
The more connections and relations are defined, the more specific tagging results are going to be available. Therefore, it is always important to build the tag database carefully.

TAS Tagger GUI can be created within the confines of TAS Platform (TAS Cloud service) or On Premise (locally installed). The appearance of Tagger is consistent with the corporate identity of TAS Platform. The visualization and the other parts of the user interface are also configurable. The particular solution depends on the customer’s needs.