Zero-Shot Transfer Learning for Event Extraction
meeting of the association for computational linguistics, Volume abs/1707.01066, 2018.
Most previous event extraction studies have relied heavily on features derived from annotated event mentions, thus cannot be applied to new event types without annotation effort. In this work, we take a fresh look at event extraction and model it as a grounding problem. We design a transferable neural architecture, mapping event mentions ...More
Full Text (Upload PDF)