Lemmatization and Parsing with TACT Preprocessing Programs [1996, rptd. 2008]
Ray Siemens · Digital Studies / Le champ numérique · 1996
This paper aims to provide a context for those intending to parse and lemmatize electronic texts using the preprocessing programs provided with TACT: PreProc, MakeDCT, TagText, and SatDCT. It outlines some recent thought on computer-assisted parsing and lemmatization, it discusses relevant controversies and concerns within the field with specific (though not exclusive) reference to texts in English, and it hopes to offer a practical orientation to the operation of the TACT programs.