Template filling is generally tackled by a pipeline of two separate supervised systems -- one for role-filler extraction and another for template/event recognition. Since pipelines consider events in isolation, they can suffer from error propagation.
We introduce a framework based on end-to-end generative transformers for this task (i.e., GTT). It naturally models the dependence between entities both within a single event and across the multiple events described in a document. Experiments demonstrate that this framework substantially outperforms pipeline-based approaches, and other neural end-to-end baselines that do not model between-event dependencies. We further show that our framework specifically improves performance on documents containing multiple events.
The aim of this study was to evaluate the clinical and radio graphical success
rates of ferric sulfate pulpotomy in human second mandibular primary molar teeth when zinc
polycarboxylate cement is used as a sub base material.