scholarly journals Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning

2021 ◽  
Author(s):  
Yucheng Zhou ◽  
Xiubo Geng ◽  
Tao Shen ◽  
Jian Pei ◽  
Wenqiang Zhang ◽  
...  
Keyword(s):  
Event Pair ◽  
External Knowledge ◽  
Knowledge Graphs

scholarly journals Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

2020 ◽  
Vol 34 (05) ◽  
pp. 8074-8081
Author(s):  
Pavan Kapanipathi ◽  
Veronika Thost ◽  
Siva Sankalp Patel ◽  
Spencer Whitehead ◽  
Ibrahim Abdelaziz ◽  
...  
Keyword(s):  
Language Processing ◽  
Prediction Accuracy ◽  
Semantic Information ◽  
Training Data ◽  
Personalized Pagerank ◽  
External Knowledge ◽  
Convolutional Networks ◽  
Textual Entailment ◽  
Knowledge Graphs ◽  
Textual Content

Textual entailment is a fundamental task in natural language processing. Most approaches for solving this problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageRank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture the structural and semantic information in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps the model to be robust and improves prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.

scholarly journals A Knowledge Retrieval Framework for Household Objects and Actions with External Knowledge

2020 ◽  
pp. 36-52
Author(s):  
Alexandros Vassiliades ◽  
Nick Bassiliades ◽  
Filippos Gouidis ◽  
Theodore Patkos
Keyword(s):  
Cognitive Robotics ◽  
Knowledge Graph ◽  
Semantic Matching ◽  
Knowledge Retrieval ◽  
Human Actions ◽  
External Knowledge ◽  
Household Environment ◽  
Knowledge Graphs ◽  
The Web ◽  
Representation Of Knowledge

Abstract In the field of domestic cognitive robotics, it is important to have a rich representation of knowledge about how household objects are related to each other and with respect to human actions. In this paper, we present a domain dependent knowledge retrieval framework for household environments which was constructed by extracting knowledge from the VirtualHome dataset (http://virtual-home.org). The framework provides knowledge about sequences of actions on how to perform human scaled tasks in a household environment, answers queries about household objects, and performs semantic matching between entities from the web knowledge graphs DBpedia, ConceptNet, and WordNet, with the ones existing in our knowledge graph. We offer a set of predefined SPARQL templates that directly address the ontology on which our knowledge retrieval framework is built, and querying capabilities through SPARQL. We evaluated our framework via two different user evaluations.

A framework for explainable deep neural models using external knowledge graphs

2020 ◽  
Author(s):  
Zachary A. Daniels ◽  
Logan D. Frank ◽  
Christopher Menart ◽  
Michael Raymer ◽  
Pascal Hitzler
Keyword(s):  
Neural Models ◽  
External Knowledge ◽  
Knowledge Graphs

scholarly journals Knowledge-Enriched Visual Storytelling

2020 ◽  
Vol 34 (05) ◽  
pp. 7952-7960
Author(s):  
Chao-Chun Hsu ◽  
Zi-Yuan Chen ◽  
Chi-Yang Hsu ◽  
Chih-Chia Li ◽  
Tzu-Yuan Lin ◽  
...  
Keyword(s):  
Short Story ◽  
Training Dataset ◽  
Generation Model ◽  
Visual Storytelling ◽  
External Resources ◽  
External Knowledge ◽  
Story Generation ◽  
Knowledge Graphs ◽  
Output Space ◽  
Better Than

Stories are diverse and highly personalized, resulting in a large possible output space for story generation. Existing end-to-end approaches produce monotonous stories because they are limited to the vocabulary and knowledge in a single training dataset. This paper introduces KG-Story, a three-stage framework that allows the story generation model to take advantage of external Knowledge Graphs to produce interesting stories. KG-Story distills a set of representative words from the input prompts, enriches the word set by using external knowledge graphs, and finally generates stories based on the enriched word set. This distill-enrich-generate framework allows the use of external resources not only for the enrichment phase, but also for the distillation and generation phases. In this paper, we show the superiority of KG-Story for visual storytelling, where the input prompt is a sequence of five photos and the output is a short story. Per the human ranking evaluation, stories generated by KG-Story are on average ranked better than that of the state-of-the-art systems. Our code and output stories are available at https://github.com/zychen423/KE-VIST.

Sharing With Whom? Processes in Internal and External Knowledge Sharing

2011 ◽  
Author(s):  
Katherine Giuca ◽  
John Schaubroeck ◽  
Abraham Carmeli ◽  
Roy Gelbard
Keyword(s):  
Knowledge Sharing ◽  
External Knowledge

Effect of networks on product innovation: empirical evidence from Indonesian SMEs

2013 ◽  
Vol 1 (2) ◽  
pp. 140-158 ◽  
Author(s):  
Nurul Indarti ◽  
Theo Postma
Keyword(s):  
Empirical Evidence ◽  
Product Innovation ◽  
Dynamic Effects ◽  
Depth Of Knowledge ◽  
External Knowledge ◽  
Software Firms ◽  
Using Data

Innovative companies generally establish linkages with other actors and access external knowledge in order to benefit from the dynamic effects of interactive processes. Using data from 198 furniture and software firms in Indonesia, this study shows that the quality of interaction (i.e. multiplexity) as indicated by the depth of knowledge absorbed from various external parties and intensity of interaction (i.e., tie intensity) are better predictors of product innovation than the diversity of interaction.

Knowledge creation in small building and construction firms

2013 ◽  
Vol 1 (1) ◽  
pp. 125-142 ◽  
Author(s):  
Susanne Durst ◽  
Ingi Runar Edvardsson ◽  
Guido Bruns
Keyword(s):  
Construction Industry ◽  
Knowledge Creation ◽  
Vital Role ◽  
Knowledge Sources ◽  
Structured Interviews ◽  
Construction Firms ◽  
External Knowledge ◽  
Body Of Knowledge ◽  
Small Building

Studies on knowledge creation are limited in general, and there is a particular shortage of research on the topic in small and medium-sized enterprises (SMEs). Given the importance of SMEs for the economy and the vital role of knowledge creation in innovation, this situation is unsatisfactory. Accordingly, the purpose of our study is to increase our understanding of how SMEs create new knowledge. Data are obtained through semi-structured interviews with ten managing directors of German SMEs operating in the building and construction industry. The findings demonstrate the influence of external knowledge sources on knowledge creation activities. Even though the managing directors take advantage of different external knowledge sources, they seem to put an emphasis on informed knowledge sources. The study´s findings advance the limited body of knowledge regarding knowledge creation in SMEs.

Mobile Software Assurance Informed through Knowledge Graph Construction: The OWASP Threat of Insecure Data Storage

2020 ◽  
Vol 2 (2) ◽  
Author(s):  
Suzanna Schmeelk ◽  
Lixin Tao
Keyword(s):  
Data Storage ◽  
Program Analysis ◽  
Web Application ◽  
Security Analysis ◽  
Knowledge Graph ◽  
Healthcare Applications ◽  
Sensitive Data ◽  
Knowledge Graphs ◽  
Mobile Malware Detection ◽  
Software Assurance

Many organizations, to save costs, are movinheg to t Bring Your Own Mobile Device (BYOD) model and adopting applications built by third-parties at an unprecedented rate.  Our research examines software assurance methodologies specifically focusing on security analysis coverage of the program analysis for mobile malware detection, mitigation, and prevention.  This research focuses on secure software development of Android applications by developing knowledge graphs for threats reported by the Open Web Application Security Project (OWASP).  OWASP maintains lists of the top ten security threats to web and mobile applications.  We develop knowledge graphs based on the two most recent top ten threat years and show how the knowledge graph relationships can be discovered in mobile application source code.  We analyze 200+ healthcare applications from GitHub to gain an understanding of their software assurance of their developed software for one of the OWASP top ten moble threats, the threat of “Insecure Data Storage.”  We find that many of the applications are storing personally identifying information (PII) in potentially vulnerable places leaving users exposed to higher risks for the loss of their sensitive data.

Sign in / Sign up

Export Citation Format

Share Document