A Generalized Knowledge Base

2009 ◽  
Author(s):  
R. Zhang ◽  
M. Gu ◽  
X. Lui
Keyword(s):  
Knowledge Base ◽  
Generalized Knowledge

Ethical Administration: An Oxymoron?

1997 ◽  
Vol 7 (2) ◽  
pp. 210-225 ◽  
Author(s):  
Kelly Mckerrow
Keyword(s):  
Decision Making ◽  
Knowledge Base ◽  
Educational Administration ◽  
Ethical Decision ◽  
Ethical Decision Making ◽  
The Core ◽  
Generalized Knowledge ◽  
Educational Administration Programs ◽  
Administration Programs

This article argues that education is a fundamentally moral enterprise and that educational administration needs to change in order to reflect ethics at its core, not at its periphery. It suggests that traditional educational administration is informed by the constructs of power and leadership and that it has developed a generalized knowledge-base on modest theoretical grounds. Together these elements preclude development of educational administration as an ethical enterprise by dominating the discourse and inhibiting the dialogue necessary for ethical decision making. The question of whether or not ethical decision making can take place within an organization is explored. Recommendations for curricular changes in educational administration programs are advanced with regard to putting ethics at the core of the curriculum instead of training in idiosyncratic particulars.

WinFriends: Building your English Knowledge-Base (Version 5.02)

2017 ◽  
Vol 20 (1) ◽  
pp. 208-220
Author(s):  
J. F. Coll
Keyword(s):  
Knowledge Base

Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference

2018 ◽  
Author(s):  
Prachi Jain ◽  
Shikhar Murty ◽  
Mausam . ◽  
Soumen Chakrabarti
Keyword(s):  
Knowledge Base ◽  
Hybrid Model ◽  
Matrix Factorization ◽  
Relation Extraction ◽  
Tensor Factorization ◽  
Evaluation Protocol

This paper analyzes the varied performance of Matrix Factorization (MF) on the related tasks of relation extraction and knowledge-base completion, which have been unified recently into a single framework of knowledge-base inference (KBI) [Toutanova et al., 2015]. We first propose a new evaluation protocol that makes comparisons between MF and Tensor Factorization (TF) models fair. We find that this results in a steep drop in MF performance. Our analysis attributes this to the high out-of-vocabulary (OOV) rate of entity pairs in test folds of commonly-used datasets. To alleviate this issue, we propose three extensions to MF. Our best model is a TF-augmented MF model. This hybrid model is robust and obtains strong results across various KBI datasets.

Sign in / Sign up

Export Citation Format

Share Document