|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Moreover, it is shown that reasonable performance can be obtained when ZEN is trained on a small corpus, which is important for applying pre-training techniques to scenarios with limited data.
However, existing methods for Chinese NER either do not exploit word boundary information from CWS or cannot filter the specific information of CWS.
A bottleneck problem with Chinese named entity recognition (NER) in new domains is the lack of annotated data.
Identifying the named entities mentioned in text would enrich many semantic applications at the downstream level.