Implicit Argument Prediction with Event Knowledge.
north american chapter of the association for computational linguistics(2018)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络