Lang.Tec
LangTec is a research-driven technology provider in semantic text analytics (NLP) and automated text generation (NLG) based out of Hamburg, Germany. For our clients, we develop innovative language technology and articificial intelligence solutions to enable the efficient processing of large amounts of text and data. Semantic text and data mining, machine learning (ML) and artificial intelligence (AI) are our core competencies. With our continually growing team of expert data scientists, computational linguists, developers and classical linguists, we have been operating successfully in the market place since 2011.
LangTec's clients comprise:
Microsoft, Bosch, Siemens, INGDiBa, Otto, German Railways, tesa, AbbVie, Elsevier, PwC, Continental, Lionbridge, Novomind, Artificial Solutions, Gracenote, facelift, VoiceBox, Prime Research, getAbstract, Appen, Hamburg University and many others.
LangTec entertains three business units:
1. Text Analytics: LangTec analyses large amounts of structured and unstructured data and provides access to their deep semantics. Drawing on a wide spectrum of techniques from computational linguistics and articificial intelligence, our solutions extract business-critical information in structured form, classify document types or uncover facts, topics or semantic relations.
2. Automated Text and Document Generation: Journalist-like, LangTec's TextWriter solution creates human-readable multilingual copy text from multiple structured data sources in just fractions of a second. In this generation process, target texts can be optimised with regards to various parameters such as SEO relevance, readability, text length, target group or output medium.
Another important application domain for text generation is automated document generation for the scalable creation of fully annotated test and training data in machine learning. LangTec's solution DocumentCreator comes into play when sufficient test and training data are hard to come by for reasons of confidentiality, copyright or simply limited volume or quality of manual annotations. DocumentCreator permits to generate highly varied synthetic test and training data with effectively no quantitative limitations.
3. Computational Linguistics: LangTec boasts many years of experience in the creation, maintenance and enhancement of linguistic resources such as phonetic lexicons, grammars, language models, ontologies, knowledge graphs, dialogue models, text normalisation engines or speech recognition grammars. LangTec focuses on all European target languages as well as selected Asian languages.
LangTec's solutions were employed in the following exemplary application contexts:
- Automated product classification in very large product portfolios
- Specific information extraction and automated workflow management for OCR-ed documents
- Media monitoring and topic prediction for the entire German-language Internet
- Deep social media monitoring for target-group-specific insights into online communication
- Automated extraction of entities from insurance texts
- Dialogue modelling for mobile assistants
- Self-learning, multilingual classification of automotive data
- Corporation-wide solution for the efficient global syncing of data
- Real-Time creation of personalised reports based on highly dynamic data streams
- Scalable generation of SEO-optimised product descriptions from data fact sheets
- Creation of highly diversified synthetic test and training data in machine learning
- Automated extraction of protein-protein interactions from biochemical research literature
Contact
LangTec Semantic Text Processing
Bundesstraße 28 a
20146 Hamburg
Germany
Phone: +49 40 18061098
info(at)langtec.de
www.langtec.de