[1707.01066] Zero-Shot Transfer Learning for Event Extraction


Computer vision has seen increasing interest in zero-shot transfer learning recently. As our training sets are finite, generalizing to unseen events, relations, entities, etc. is key. Huang et al. frame event extraction as grounding rather than classification, which allows them to generalize to new events. Related: Levy et al. (CoNLL, 2017) who generalize to unseen relations by framing relation extracting as reading comprehension.

Linkedin Revue

Want to receive more content like this in your inbox?