Ready to Start?
TXTWerk is a lightweight text analysis framework that allows you to easily extract metadata from English or German texts and deliver semantic context to unstructured texts by simply integrating it into your workflow. By applying complex linguistic and statistical algorithms, TXTWerk can read and understand your text at high speed. Whether you want to process 1000 or 10 billion documents, TXTWerk recognizes the most important keywords, people, places, organizations, events and other concepts and links found entities and concepts to one of the best known knowledge sources: Wikidata. This linking and the use of Linked Open Data opens up completely new possibilities for further processing. TXTWerk not only finds known persons, but is also able to recognize completely unknown entities in texts or use customer defined knowledge sources to adapt TXTWerk to a specific domain.
TXTWerk Features
Entity Recognition and Linking
TXTWerk identifies entities (persons, locations, events, organisations, or job titles) from your input text and links them to Wikidata. Supported Languages: German and English
Open Domain Entity Recognition
TXTWerk identifies unknown entities (persons, locations) from your input text even if they are unknown to Wikidata. Supported Languages: German and English
Concept Tagging
TXTWerk finds concepts in your input text and links them to Wikidata. If you have the Wikidata URI, you can put even more semantics in your text. Supported Languages: German and English
Keyword Extraction
TXTWerk identifies topic keywords (tags) in your text. We use sophisticated statistical algorithms and natural language processing technology to analyze your data. You can use the extracted keywords to index content, generate tag clouds, and more. Supported Languages: German
Category Classification
TXTWerk automatically classifies you content into different categories. We use the latest machine learning techniques. No need for manual classification anymore. Supported Languages: German
Date Recognition
Calendar dates will be recognized in your input text and represented in a normalized structured form. This even works for relative time expressions such as "yesterday", "two weeks ago" or "a year ago". Supported Languages: German
Plans
Evaluation (Free)
Entity Recognition with Wikidata URIs |
Concept Tagging with Wikidata URIs |
Keyword Tagging |
Classification |
Date Recognition |
Text Length up to 10,000 Characters |
Max. 500 Calls / Day |
10,000 API Calls / Month |
Free for 1 Month |
Enterprise
Entity Recognition with Wikidata URIs |
Concept Tagging with Wikidata URIs |
Keyword Tagging |
Classification |
Date Recognition |
Text Length up to 200,000 Characters |
Flexible |
Flexible |
Monthly Subscription |
Contact Us
Want to say hello? Want to know more about us? Give us a call or drop us an email and we will get back to you as soon as we can.
About Us
TXTWerk is the textmining API of Neofonie GmbH, a Berlin based solution and fullservice provider specialized on portals, search, social media, e-publishing, and mobile application.Read more
Imprint
Neofonie GmbH
Robert-Koch-Platz 4
10115 Berlin, Germany
Phone: +49 30 24627-0
Website: https://www.neofonie.de
Amtsgericht Berlin-Charlottenburg
HRB 67 460 - Sitz Berlin
Geschäftsführung:
Thomas Kitlitschko
USt-ID: DE 194 693 995