Modeling covert event retrieval in logical metonymy: probabilistic and distributional accounts

Logical metonymies (The student finished the beer) represent a challenge to compositionality since they involve semantic content not overtly realized in the sentence (covert events → drinking the beer). We present a contrastive study of two classes of computational models for logical metonymy in German, namely a probabilistic and a distributional, similarity-based model. These are built using the SDEWAC corpus and evaluated against a dataset from a self-paced reading and a probe recognition study for their sensitivity to thematic fit effects via their accuracy in predicting the correct covert event in a metonymical context. The similarity-based models allow for better coverage while maintaining the accuracy of the probabilistic models.