TextGrid : The Lemmatizer Tool

The Lemmatizer Tool consists of three elements: An input field, a configuration field and a results field. If “Lemmatize Wordform” is chosen, the input field is dedicated to a German wordform. If “Lemmatize file” is selected, the “BatchLemmatizer” for whole lemmatizing whole documents is opened and you can choose between lemmatizing plain ASCII text, a German Wordform List or tokenized TEI-conform XML depending on the format of your document. Click “Specify Input File” to select and upload your file from your computer. Make sure you have selected the corresponding file format.

In the configuration field the current form of the analysis is shown. Click “Make (Other) Configuration” to change it. A dialog opens in which you can change the output format and the lexicon. You can also set various options for the analysis: Only lemmatizing, disambiguation, guesser for unknown wordforms, fuzzy search and Zlib Compression.

After clicking “Start Lemmatizer!”, the results are displayed in the result field below the configuration field. If you want to save the result of lemmatizing a file, use the “Save Output” button at the bottom of the result field.