Integrating a Lightweight Information Agent with the Cyc Knowledge Base

Author(s):  
Kendall Lister ◽  
Leon Sterling
2020 ◽  
Vol 25 (2) ◽  
pp. 124-133
Author(s):  
Adeel Munawar ◽  
Syed Ali Raza ◽  
Awais Qasim

AbstractDue to the rapid increase in the demand for information that supports tourists after, before, and during the trip, many tour systems are available. However, these systems are not able to successfully replace a human facilitator that is expensive to hire. The primary key qualities of a human tourist guide are his/her knowledge, communication skills, and interpretation of destination attractions. Traditional tourist facilitator systems are lacking in these qualities. The main idea of the research is to design an agent to guide tourists, provide them accurate information about visitable places, without having any bound for a specific region and it will have human-like communication skills along with the point of interest knowledge, which depends on its internal knowledge base as well as its online searching techniques.


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

Author(s):  
Prachi Jain ◽  
Shikhar Murty ◽  
Mausam . ◽  
Soumen Chakrabarti

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