| Popis: |
This paper focuses on Predicate Sense Disambiguation (PSD) based on PropBank guidelines. Different approaches to this task have been proposed, from purely supervised or knowledge-based, to recently hybrid approaches that have shown promising results. We introduce one of the hybrid approaches - a PSD pipeline based on both supervised models and handcrafted rules. To train three supervised POS, DEP and POS DEP models we used syntactic features (lemma, part-of-speech tag, dependency parse) and semantic features (semantic role labels). These features enable per-token classification, which to be applied to unseen words, requires handcrafted rules to make predictions specifically for nouns in light verb constructions, unseen verbs and unseen phrasal verbs. Experiments were done on newly- developed dataset and the results show a token-level accuracy of 96% for the proposed PSD pipeline. |
