Event Identification as a Decision Process with Non-linear Representation of Text
This work addresses event identification for document analysis, presenting an incremental improvement with a hybrid model combining supervised and reinforcement learning.
The authors tackled event identification in documents by proposing the scale-free Identifier Network (sfIN), which encodes documents into multi-scale memory stacks and extracts events via multi-scale actions, achieving more efficient processing of long documents.
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.