LingRep - Contact
Frequently Asked Questions


Here you find answers to common questions together about LingRep. If anything is missing, please let us know!



Customization & Administration

What is the standard process to make efficient use of LingRep


As LingRep offers highly customized text analytics, the first step is to work out the requirements based on the project goals together with the partner/customer. The result includes the components plus their configuration data used in the workflow. In a next step, the linguistic resources are defined that underlay the components (i.e., dictionaries, ontologies, rules, acronyms, events, sentiment, etc.). Finally, the workflow is prepared technically and made accessible via web services.

What about confidential data?


LingRep comes as cloud-based or dedicated solution. The pros of the cloud-based approach are hosted infrastructure, maintenance, and the price. In case of confidential texts a dedicated in-house solution is often preferred. The benefits here are in-house confidentiality, performance, and multiple environments.

How about linguistic partnerships?


LingRep allows for integration of arbitrary components and external services. If you are likely to join the LingRep community, you are very welcome to contact us. LingRep maintains partnerships with individuals and commercial partners, such as the DFKI in Saarbrücken, Germany.















Capabilities of LingRep

Which languages are currently supported by LingRep?


LingRep allows for integration of arbitrary components and external services. If you are likely to join the LingRep community, you are very welcome to contact us. LingRep maintains partnerships with individuals and commercial partners, such as the DFKI in Saarbrücken, Germany.

What components are available within Lingrep?


LingRep offers a broad range of components available for workflow generation, which are freely combinable and interchangeable. Some components depend on the output of preceding components. Many of these components have been developed for LingRep exclusively and cover Tokenizers, Sentence Splitters, Structural Annotators, Dictionary Lookup, Regular Expressions, Named Entity Recognizers, Acronym and Abbreviation Resolvers, Dereferencers, Number and Value Annotators, Event Detectors, Text Quantification (e.g., Sentiment), Language Guessers, Syntax Parsers, Classifiers, and other highly specialized annotators. In addition to that other well established frameworks such as GATE and OpenNLP have been integrated, so all of their components are available as well. Last but not least third-party linguistic service providers such as OpenCalais are also accessible via LingRep.

What technologies are applied by the LingRep components?


The technologies exploited in the components strongly vary and subsume mechanisms such as high performance hard-coded, lookup-based, rule-based, statistical/stochastical, human-trained, and machine-learning elements.