Answers are grounded in this paper and cite their sources.
We present the results of clustering experiments with a number of different evaluation sets using dependency based word spaces. Contrary to previous results we found a clear advantage using a parsed corpus over word spaces constructed with the help of simple patterns. We achieve considerable gains in performance over these spaces ranging between 9 and 13% in absolute terms of cluster purity.
No takes yet. Share an insight, caveat, or question.
Rothenhäusler et al. (2009) studied this question.