id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_3eoycspfm5bwthv6g7zteuo6ky	Hang Yan	A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing	2020	15	.pdf	application/pdf	9222	914	66	A Graph-based Model for Joint Chinese Word Segmentation and BERT is combined, our model can substantially reduce the performance gap of dependency parsing between joint models and previous joint models mainly adopted a transitionbased parsing framework to integrate the word segmentation, POS tagging, and dependency parsing. Because the segmentation is a characterlevel task and dependency parsing is a word-level and CTB-9, our model achieves state-ofthe-art score in joint CWS and dependency joint POS tagging and dependency parsing model joint inference model for word segmentation, POS F1seg and F1udep are the F1 score for Chinese word segmentation and unlabeled dependency parsing, Owing to the joint decoding of CWS and dependency parsing, we can utilize the characterlevel pre-trained language model BERT. joint Chinese word segmentation and dependency joint decoding between Chinese word segmentation and dependency parsing, our model can use Joint Segmentation, POS Tagging, and Dependency Parsing	./cache/work_3eoycspfm5bwthv6g7zteuo6ky.pdf	./txt/work_3eoycspfm5bwthv6g7zteuo6ky.txt