A knowledge graph-based content selection model for data-driven text generation

2017 ◽  
Vol 9 (3/4) ◽  
pp. 205
Author(s):  
Jun Peng Gong ◽  
Juan Cao ◽  
Peng Zhou Zhang
Keyword(s):  
Selection Model ◽  
Data Driven ◽  
Knowledge Graph ◽  
Text Generation ◽  
Content Selection

scholarly journals Data-to-Text Generation with Content Selection and Planning

2019 ◽  
Vol 33 ◽  
pp. 6908-6915 ◽  
Author(s):  
Ratish Puduppully ◽  
Li Dong ◽  
Mirella Lapata
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Network Models ◽  
Text Generation ◽  
Neural Network Models ◽  
Generation Task ◽  
Content Selection ◽  
End To End ◽  
Two Stages

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

scholarly journals Hybrid feature selection model based on machine learning and knowledge graph

2021 ◽  
Vol 2079 (1) ◽  
pp. 012028
Author(s):  
Xiaoqing Peng ◽  
Yong Shuai ◽  
Yaxi Gan ◽  
Yaokai Chen
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Learning Algorithms ◽  
Selection Model ◽  
Knowledge Graph ◽  
Model Based ◽  
Text Features ◽  
Learning Data

Abstract Aiming at the problem that the current feature selection algorithm can not adapt to both supervised learning data and unsupervised learning data, and had poor feature interpretability, this paper proposed a hybrid feature selection model based on machine learning and knowledge graph. By the idea of hybridization, this model used supervised learning algorithms, unsupervised learning algorithms and knowledge graph technology to model from the perspective of data features and text features. Firstly, the data-based feature weights were obtained through the machine learning model, and then the text-based weights were obtained by using the knowledge graph technology, and the weight sets are combined to obtain a feature matrix with good explanatory properties that meets both the data and text features. Finally, the case analysis proves that the method proposed in this paper has good effects and interpretability.

scholarly journals The roles of data management and analytics in industry 4.0 ecosystems

2020 ◽  
Author(s):  
Hendro Wicaksono
Keyword(s):  
Artificial Intelligence ◽  
Industry 4.0 ◽  
Linked Data ◽  
Data Analytics ◽  
Industrial Revolution ◽  
Data Driven ◽  
Knowledge Graph ◽  
Fourth Industrial Revolution ◽  
Global Access ◽  
Integration Data

The presentation introduces the technologies associated with the fourth industrial revolution which rely on the concept of artificial intelligence. Data is the basis of functioning artificial intelligence technologies. The presentation also explains how data can revolutionize the business by providing global access to physical products through an industry 4.0 ecosystem. The ecosystem contains four pillars: smart product, smart process, smart resources (smart PPR), and data-driven services. Through these four pillars, the industry 4.0 can be implemented in different sectors. The presentation also provides some insights on the roles of linked data (knowledge graph) for data integration, data analytics, and machine learning in industry 4.0 ecosystem. Project examples in smart city, healthcare, and agriculture sectors are also described. Finally, the presentation discusses the implications of the introduced concepts on the Indonesian context.

A novel data-driven robust framework based on machine learning and knowledge graph for disease classification

2020 ◽  
Vol 102 ◽  
pp. 534-548
Author(s):  
Zhenfeng Lei ◽  
Yuan Sun ◽  
Y.A. Nanehkaran ◽  
Shuangyuan Yang ◽  
Md. Saiful Islam ◽  
...  
Keyword(s):  
Machine Learning ◽  
Disease Classification ◽  
Data Driven ◽  
Knowledge Graph ◽  
Robust Framework

Business Ethics Competencies

2015 ◽  
pp. 201-223
Author(s):  
David Cramm ◽  
Ronel Erwee
Keyword(s):  
Business Ethics ◽  
Document Analysis ◽  
Ethics Training ◽  
Competency Model ◽  
Selection Model ◽  
Content Selection ◽  
The Us ◽  
Business Ethics Training ◽  
Two Phases ◽  
Shed Light

This chapter aims to discuss the divergent views of 102 practitioners and academics about business ethics competencies and potential implications for business ethics training. It presents, first, an introduction to the nature of the misalignment between academia and industry and, second, business ethics training issues and controversies. Next, the two phases of the research, including document analysis and a survey in Canada and the US, are noted. When considering practitioner needs, potentially over- or under-emphasized competencies are identified by means of a survey to shed light on the extent of this misalignment, so that future instructional efforts can focus on increasing content considered by practitioners to be under-emphasized, while reducing the content considered to be over-emphasized. Finally, a proposed business ethics competency model is provided, as well as a comprehensive content selection model for business ethics development, designed and recommended for business ethics practitioners and academics.

Business Ethics Competencies

2015 ◽  
pp. 1371-1393
Author(s):  
David Cramm ◽  
Ronel Erwee
Keyword(s):  
Business Ethics ◽  
Document Analysis ◽  
Ethics Training ◽  
Competency Model ◽  
Selection Model ◽  
Content Selection ◽  
The Us ◽  
Business Ethics Training ◽  
Two Phases ◽  
Shed Light

This chapter aims to discuss the divergent views of 102 practitioners and academics about business ethics competencies and potential implications for business ethics training. It presents, first, an introduction to the nature of the misalignment between academia and industry and, second, business ethics training issues and controversies. Next, the two phases of the research, including document analysis and a survey in Canada and the US, are noted. When considering practitioner needs, potentially over- or under-emphasized competencies are identified by means of a survey to shed light on the extent of this misalignment, so that future instructional efforts can focus on increasing content considered by practitioners to be under-emphasized, while reducing the content considered to be over-emphasized. Finally, a proposed business ethics competency model is provided, as well as a comprehensive content selection model for business ethics development, designed and recommended for business ethics practitioners and academics.

scholarly journals End-to-End Argumentation Knowledge Graph Construction

2020 ◽  
Vol 34 (05) ◽  
pp. 7367-7374
Author(s):  
Khalid Al-Khatib ◽  
Yufang Hou ◽  
Henning Wachsmuth ◽  
Charles Jochim ◽  
Francesca Bonin ◽  
...  
Keyword(s):  
Large Scale ◽  
Question Answering ◽  
Knowledge Graph ◽  
Exploratory Search ◽  
Text Generation ◽  
Fake News ◽  
High Quality ◽  
Web Based ◽  
Knowledge Graphs ◽  
End To End

This paper studies the end-to-end construction of an argumentation knowledge graph that is intended to support argument synthesis, argumentative question answering, or fake news detection, among others. The study is motivated by the proven effectiveness of knowledge graphs for interpretable and controllable text generation and exploratory search. Original in our work is that we propose a model of the knowledge encapsulated in arguments. Based on this model, we build a new corpus that comprises about 16k manual annotations of 4740 claims with instances of the model's elements, and we develop an end-to-end framework that automatically identifies all modeled types of instances. The results of experiments show the potential of the framework for building a web-based argumentation graph that is of high quality and large scale.

Sign in / Sign up

Export Citation Format

Share Document