DE  EN  
  >  TextGrid

Lemmatizer

The Lemmatizer tool can be used to morphologically analyze German word forms, such as to find the dictionary form of a word (for example, the lemma of the third-person present verb "is" would be "to be.") You can also perform other, more complex functions, such as morpho-syntactic analyses involving case, tense, number, gender, and person of a word.

You can lemmatize complete files with the function Lemmatize File, or interactively use the tool Lemmatize Wordform for a single word analysis. The command "Search Historic" is used to manage and search morpho-syntactic information about historic word forms. TextGrid uses the SFST (Stuttgart Finite State Library) database for the morphological analysis of New High German words.

The linguistic annotation can also be integrated into a TEI/XML encoded file. If the input file is tokenized and single tokens are enclosed in <w> tags, the lemmatizer adds the attributes lemma and ana within the <w> tag automatically, thus providing the lemma and part of speech information. The result is a valid XML file that can be used for further processing.

Further information is available here:

R2.3: User's Manual TextGrid-Tools (on page 62-67)

TextGrid 1.0

Users Meeting