On the Utility of Conjoint and Compositional Frames and Utterance Boundaries as Predictors of Word Categories

This paper reports the results of a series of connectionist simulations aimed at establishing the value of different types of contexts as predictors of the grammatical categories of words. A comparison is made between ‘compositional’ frames (Monaghan & Christiansen, 2004), and noncompositional or ‘conjoint’ frames (Mintz, 2003). Attention is given to the role of utterance boundaries both as a category to be predicted and as a predictor. The role of developmental constraints is investigated by examining the effect of restricting the analysis to utterance-final frames. In line with results reported by Monaghan and Christiansen compositional frames are better predictors than conjoint frames, though the latter provide a small performance improvement when combined with compositional frames. Utterance boundaries are shown to be detrimental to performance when included as an item to be predicted while improving performance when included as a predictor. The utility of utterance boundaries is further supported by the finding that when the analysis is restricted to utterance-final frames (which are likely to be a particularly important source of information early in development) frames including utterance boundaries are far better predictors than lexical frames.