Implicit Argument Prediction with Event Knowledge
This addresses a challenge in natural language processing for tasks like information extraction, though it is incremental as it builds on prior work with neural methods.
The paper tackles the problem of extracting implicit arguments not syntactically connected to predicates by proposing a model trained on a cloze task with automatically generated data, achieving superior performance on synthetic and natural datasets.
Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. We propose to train models for implicit argument prediction on a simple cloze task, for which data can be generated automatically at scale. This allows us to use a neural model, which draws on narrative coherence and entity salience for predictions. We show that our model has superior performance on both synthetic and natural data.