Event Extraction by Answering (Almost) Natural Questions

Code

• github.com/xinyadu/eeqa
  OfficialIn paperpytorch★ 207
• github.com/zhaoyuesun/phee
  pytorch★ 24
• github.com/xinyadu/rgqa
  pytorch★ 17

Abstract

The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation. To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task that extracts the event arguments in an end-to-end manner. Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (zero-shot learning setting).

Tasks

Reproductions