Extra Large Sequence Transformer Model for Chinese Word Segment
Keyword(s):
Abstract Chinese word segment is widely studied in document analysis. The accuracy of the current popular word segment model, LSTM+CRF, is still not satisfactory. Models trained by the popular dataset often fails in the out-domain situation. In this paper, combining the Transformer-XL layer, the Fully-Connect layer, and the Conditional Random Field layer, the proposed model improved 3.23% in the macro-F1 score, comparing to the BERT+CRF model, on the MSR2005 Chinese word segment test dataset.
Keyword(s):
Keyword(s):
2019 ◽
Vol 1168
◽
pp. 042008
Keyword(s):