A comparison of structural correspondence learning and self-training for discriminative parse selection
Barbara Plank · 2009
This paper evaluates two semi-supervised techniques for the adaptation of a parse selection model to Wikipedia domains. The techniques examined are Structural Correspondence Learning (SCL) (Blitzer et al., 2006) and Self-training (Abney, 2007; McClosky et al., 2006). A preliminary evaluation favors the use of SCL over the simpler self-training techniques.