Video Captioning with Semantic Information from the Knowledge Base

2017 ◽  
Author(s):  
Dan Wang ◽  
Dandan Song
Keyword(s):  
Knowledge Base ◽  
Semantic Information ◽  
Video Captioning

Ontology Self-Perfect Based Lexical Chain for IE

2014 ◽  
Vol 644-650 ◽  
pp. 1972-1975
Author(s):  
Rui Gao ◽  
Yan Zhang ◽  
Hua Deng ◽  
Jin Si ◽  
Xiao Meng
Keyword(s):  
Information Extraction ◽  
Knowledge Base ◽  
Semantic Information ◽  
Series Of Experiments ◽  
Lexical Chain

The perfection of an ontology knowledge base is essential to the research of ontology-based information extraction (IE). Information extraction in short documents with sparse vocabularies in the ontology will cause the problem of semantic deviation. That will affect the indexes of information extraction in short documents. In this paper, we propose a method of using lexical chain to perfect the ontology knowledge base automatically in order to cover the shortage of manual constructed ontology. We can solve the problem of semantic information deficiency caused by the sparse vocabulary in the ontology effectively through the use of this method. We proved the validity of our method through the series of experiments we conducted.

Construction of XBRL Semantic Metamodel and Knowledge Base Based on Ontology

2014 ◽  
Vol 571-572 ◽  
pp. 1119-1128
Author(s):  
Wen Li Wang ◽  
Min Huang ◽  
Ying Wang
Keyword(s):  
Semantic Web ◽  
Knowledge Base ◽  
Financial Reporting ◽  
Semantic Information ◽  
Semantic Web Technologies ◽  
Semantic Level ◽  
Web Technologies ◽  
Translation Mechanism ◽  
Owl Ontology

In order to improve the interoperability of XBRL format financial reporting on the semantic level, a novel XBRL financial reporting metamodel and a fact data semantic metamodel are proposed, which uses the Semantic Web technologies and Ontology theory. Then, a XBRL knowledge base is constructed based on this metamodel .Using the metamodel-based translation mechanism from XBRL to OWL / RDF, all the semantic information in XBRL taxonomy and instance documents is translated into OWL ontology and RDF instance. Finally, a knowledge base covering the semantic information of financial reporting domain is constructed.

scholarly journals Hypergraph Convolutional Network for Multi-Hop Knowledge Base Question Answering (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13801-13802
Author(s):  
Jiale Han ◽  
Bo Cheng ◽  
Xu Wang
Keyword(s):  
Knowledge Base ◽  
Question Answering ◽  
Semantic Information ◽  
Semantic Relation ◽  
Experimental Results ◽  
Data Correlation ◽  
Convolutional Network ◽  
Related Data ◽  
Convolutional Networks ◽  
High Level

Graph convolutional networks (GCN) have been applied in knowledge base question answering (KBQA) task. However, the pairwise connection between nodes of GCN limits the representation capability of high-order data correlation. Furthermore, most previous work does not fully utilize the semantic relation information, which is vital to reasoning. In this paper, we propose a novel multi-hop KBQA model based on hypergraph convolutional network. By constructing a hypergraph, the form of pairwise connection between nodes and nodes is converted to the high-level connection between nodes and edges, which effectively encodes complex related data. To better exploit the semantic information of relations, we apply co-attention method to learn similarity between relation and query, and assign weights to different relations. Experimental results demonstrate the effectivity of the model.

Research on Measuring Semantic Correlation Based on the Wikipedia Hyperlink Network

2013 ◽  
Vol 1 (3) ◽  
pp. 1-11 ◽  
Author(s):  
Feiyue Ye ◽  
Feng Zhang
Keyword(s):  
Knowledge Base ◽  
Large Scale ◽  
Semantic Information ◽  
Semantic Relatedness ◽  
New Method ◽  
Test Set ◽  
Semantic Correlation ◽  
Calculation Results ◽  
New Ideas ◽  
Online Encyclopedia

As a free online encyclopedia with a large-scale of knowledge coverage, rich semantic information and quick update speed, Wikipedia brings new ideas to measure semantic correlation. In this paper, the authors present a new method for measuring the semantic correlation between words by mining rich semantic information that exists in Wikipedia. Unlike the previous methods that calculate semantic relatedness merely based on the page network or the category network, the authors' method not only takes into account the semantic information of the page network, it also combines the semantic information of the category network and it improves the accuracy of the results. Besides this, the authors analyze and evaluate the algorithm by comparing the calculation results with famous knowledge base (e.g., Hownet) and traditional methods based on Wikipedia on the same test set and prove its superiority.

SPARQL for Semantic Information Retrieval from RDF Knowledge Base

2016 ◽  
Vol 41 (7) ◽  
pp. 351-354
Author(s):  
Gunnam Swathi ◽  
S. Mahaboob Hussain ◽  
Prathyusha Kanakam ◽  
D. Surya narayana
Keyword(s):  
Information Retrieval ◽  
Knowledge Base ◽  
Semantic Information ◽  
Semantic Information Retrieval

scholarly journals Semantic Digital Twins for Retail Logistics

2021 ◽  
pp. 129-153
Author(s):  
Michaela Kümpel ◽  
Christian A. Mueller ◽  
Michael Beetz
Keyword(s):  
Knowledge Base ◽  
Semantic Information ◽  
Retail Store ◽  
Scene Graph ◽  
Robot Systems ◽  
Semantically Enhanced ◽  
Online Stores ◽  
Visualization And Simulation ◽  
Store Environment ◽  
Stationary Retail

AbstractAs digitization advances, stationary retail is increasingly enabled to develop novel retail services aiming at enhancing efficiency of business processes ranging from in-store logistics to customer shopping experiences. In contrast to online stores, stationary retail digitization demands for an integration of various data like location information, product information, or semantic information in order to offer services such as customer shopping assistance, product placement recommendations, or robotic store assistance.We introduce the semantic Digital Twin (semDT) as a semantically enhanced virtual representation of a retail store environment, connecting a symbolic knowledge base with a scene graph. The ontology-based symbolic knowledge base incorporates various interchangeable knowledge sources, allowing for complex reasoning tasks that enhance daily processes in retail business. The scene graph provides a realistic 3D model of the store, which is enhanced with semantic information about the store, its shelf layout, and contained products. Thereby, the semDT knowledge base can be reasoned about and visualized and simulated in applications from web to robot systems. The semDT is demonstrated in three use cases showcasing disparate platforms interacting with the semDT: Optimization of product replenishment; customer support using AR applications; retail store visualization, and simulation in a virtual environment.

Sign in / Sign up

Export Citation Format

Share Document