Collocational word similarity is considered a source of text cohesion that is hard to measure and quantify. The work presented here explores the use of information from a training corpus in measuring word similarity and evaluates the method in the text segmentation task. An implementation, the V e c T i l e system, produces similarity curves over texts using pre-compiled vector representations of the contextual behavior of words. The performance of this system is shown to improve over that of the purely string-based TextTiling algorithm (Hearst, 1997). 1 Background .
