Paper Info
Title
An Investigation of Potential Function Designs for Neural CRF
Abstract
The neural linear-chain CRF model is one of the most widely-used approach to sequence labeling. In this paper, we investigate a series of increasingly expressive potential functions for neural CRF models, which not only integrate the emission and transition functions, but also explicitly take the representations of the contextual words as input. Our extensive experiments show that the decomposed quadrilinear potential function based on the vector representations of two neighboring labels and two neighboring words consistently achieves the best performance.
Year
DOI
Venue
2020
10.18653/V1/2020.FINDINGS-EMNLP.236
EMNLP
DocType
Volume
Citations 
Conference
2020.findings-emnlp
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Zechuan Hu100.68
Yong Jiang2109.25
Nguyen Bach322.11
Tao Wang401.01
Zhongqiang Huang554.51
Fei Huang627.54
KeWei Tu713625.00