Exploiting Explicit Annotations and Semantic Types for Implicit Argument Resolution

Following the frame semantics paradigm, we present a novel strategy for solving null-instantiated arguments. Our method learns probability distributions of semantic types for each Frame Element from explicit corpus annotations. These distributions are used to select the most probable missing implicit arguments together with its most probable fillers. We empirically demonstrate that our method outperforms the systems evaluated on the Sem Eval 2010 task 10 dataset.