We present an event extraction framework

to detect event mentions and extract events

from the document-level financial news.

Up to now, methods based on supervised

learning paradigm gain the highest perfor-

mance in public datasets (such as ACE

20051, KBP 20152). These methods heav-

ily depend on the manually labeled train-

ing data. However, in particular areas,

such as financial, medical and judicial do-

mains, there is no enough labeled data due

to the high cost of data labeling process.

Moreover, most of the current methods

focus on extracting events from one sen-

tence, but an event is usually expressed

by multiple sentences in one document.

To solve these problems, we propose a

Document-level Chinese Financial Event

Extraction (DCFEE) system which can au-

tomatically generate a large scaled labeled

data and extract events from the whole

document. Experimental results demon-

strate the effectiveness of it.