TEXTA full search enables to concentrate the enterprise’s documents and subject them to fast searches. If necessary, we add the public data collections important to the enterprise. TEXTA full search enables to conduct basic searches, prefix searches and phrase searches from all indexed documents.
Full search is beneficial to the enterprises, which create lots of texts and wish to quickly find out if similar tasks have been already dealt by someone. Likewise, it is beneficial to the enterprises that engage daily with voluminous offers. Provides opportunity to instantly find offers that correspond to the same parameter, thus significantly saving the resources spent on the work.
Data safety is guaranteed for the customer with the installation of TEXTA software on the local infrastructure.SEE EXAMPLE
TEXTA LAW is an environment for legal experts who wish a fast and modern access to the public legal information. It contains the judicial decisions made public in the home pages of the Supreme Court (www.riigikohus.ee) and the State Gazette (www.riigiteataja.ee), graduation theses of the Faculty of Law at the University of Tartu, contentions of public procurements, judicial decisions of the Court of Justice of the European Union and decisions of the Consumer Protection Board.
Besides searches, TEXTA Law user interface provides the possibility to visualise search results.SEE EXAMPLE
For analyzing the data, we recommend to look at our TEXTA Toolkit!
includes the tools, which are necessary for the text analytics or solutions based on the latter. TEXTA enables fast searches and analyses from texts, to classify documents and extract information from them. The content of toolkit can be configured according to the needs of the customer and is accessible as a cloud service or installed to the customer’s infrastructure. The toolkit contains the following applications:
Application enables real time searches from the datasets and to concentrate results across different data fields. At the same time, the tool provides the opportunity to conduct basic searches, prefix searches and excluding searches.
Application enables to identify multi-word semiotic units from the text corpus (e.g. pain in chest or bruising of left hand) in order to describe information conveyed with several concepts. Output of the application can be used for the improvement of searches and creation of training datasets.
Application helps to identify synonymous word forms from the enterprise’s texts, which are helpful in making more precise searches or choosing a training data for the classifier. To find synonyms, the newest machine learning algorithms based on the artificial neurowebs are used.
Application enables planar outlining of word forms found in the text and form concepts out of the latter, which help to describe the information in data.
Application is meant for partitioning information, enabling a user to create the limited grammar of languages in order to describe information within the text.
Application enables automatic categorisation of documents into the predefined classes. A user can dictate the appropriate classes and training data.
According to the wishes of customers, we create solutions that focus on the accomplishment of definite tasks. Automatic treatment of incoming e-mails or categorisation and filtration of web comments can be put forward as an example.READ MORE