Machine learning

Physics

Complex event processing

Data mining

Artificial intelligence

Economics

Chemistry

Management

Information extraction

Programming language

Natural language processing

Event (particle physics)

Task (project management)

Preprocessor

Computer science

Chromatography

Question answering

Extraction (chemistry)

Biochemistry

Quantum mechanics

Process (computing)

Argument (complex analysis)

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 (i.e., in a zero-shot learning setting).

Event Extraction by Answering (Almost) Natural Questions