Using Dependency Relations for Text Classification


We investigate the use of syntactically related pairs of words for the task of text classification. The set of all pairs of syntactically related words should intuitively provide a better description of what a document is about, than the set of proximity-based N-grams or selective syntactic phrases. We generate syntactically related word pairs using a… (More)

8 Figures and Tables


  • Presentations referencing similar topics