We propose scale-free Identifier Network(sfIN), a novel model for event identification in documents. In general, sfIN first encodes a document into multi-scale memory stacks, then extracts special events via conducting multi-scale actions, which can be considered as a special type of sequence labelling. The design of large scale actions makes it more efficient processing a long document. The whole model is trained with both supervised learning and reinforcement learning.
@article{arxiv.1710.00969,
title = {Event Identification as a Decision Process with Non-linear Representation of Text},
author = {Yukun Yan and Daqi Zheng and Zhengdong Lu and Sen Song},
journal= {arXiv preprint arXiv:1710.00969},
year = {2017}
}