Our Package for Extracting General Linguistic Information from Texts
- You want to know which is the vocabulary that is used in your documents?
- You want to determine the frequency of occurrence for every single word form and its corresponding lemma?
- You want grammatical information to be assigned to each word form, or orthographic errors to be spotted?
- You want to have information about register of the major vocabulary (pejorative, colloquial, …)?
LCCore, our powerful package for text analysis based on linguistic processing provides you with all this information – and even more!
LCCore is based on a deep morphological analysis of each word occurring in a text. Morpheme lexicons with a rather complete coverage of different languages allow for lemmatisation and the determination of a broad range of linguistic properties. Morphological derivation and other types of word formation are systematically accounted for. Specific properties of languages such as the productive compounding in German are fully determined. For German there is almost no word that we do not know.
In addition, for German we maintain a lemma dictionary of more than 750 000 lemmas comprising many special purpose words with semantic and pragmatic information. Every year between 10 000 and 12 000 new entries are added. The resource is completed with special dictionaries for abbreviations, measures, and idioms.
The grammatical analysis module of LCCore uses the knowledge of the morphological analysis to identify grammatical structures. Noun phrases, verb groups and sentence patterns are identified in order to spot and remove ambiguities. This ensures that the intended reading of words and sentences is more easily recognised.
- compound analysis
- grammatical features
- multi-word units
- abbreviations and acronyms
- spelling correction
- technical terms
- register (slang)
- grammatical structure
- German (AT, CH, DE)
- English (GB, US)
- others on request
If you have further questions, or if you would like to know how we can help you with your specific requirements, do not hesitate to contact us.
This page as a download-PDF.