Special Issue of the JWS on
Representation Learning for the Semantic Web
The Journal of Web Semantics invites submissions for a special issue on representation learning for the Semantic Web, to be edited by Heiko Paulheim, Volker Tresp and Zhiyuan Liu.
Submissions are due by 30th November 2017.
In the past years, learning vector space
embeddings has rapidly gained attention, first in the natural language
processing community with the advent of word2vec, and more recently also in the
Semantic Web community, e.g., with the adaptations RDF2vec or node2vec, as well
as the RESCAL/HolE and Trans* family. Their properties - the representation of
entities in a dense vector space, the proximity of semantically related
entities, and the preservation of the direction of semantic relations - make
them interesting for many applications.
There are various ways of creating such
embeddings. They range from applying the word2vec paradigm to sequences derived
from graphs to translation learning and tensor factorization. Those methods
differ both in their scalability on different types of input datasets, as well
as in the characteristics of the resulting embeddings.
At the same time, novel use cases for embeddings
of Semantic Web data are discussed. Those applications range from Semantic Web
specific use cases, such as link prediction in knowledge graphs, to general
applications, such as recommender systems and decision support systems. In many
of those fields, approaches leveraging embeddings have recently been reported
to outperform traditional techniques.
The aim of this special issue is to present
latest advances in neural embeddings for the Semantic Web, as well as novel
applications. Topics of submissions include, but are not limited to:
- Novel methods for learning embeddings
- Theory of representation learning for the Semantic Web
- Embeddings of ontologies and knowledge graphs
- Joint embeddings of Semantic Web and non-Semantic Web data (e.g., text, media, ...)
- Paradigms for sharing and reusing embeddings
- Embedding systems for modeling human memories
- Scalability of embedding learning
- Implementations
- Reusable embeddings for popular Semantic Web resources, e.g., DBpedia or Wikidata
- Software frameworks for learning and using embeddings
- Experimental studies and benchmarks
- Application areas of embeddings, e.g. recommender systems, entity search or named entity disambiguation
Important Dates
- Submission deadline: November 30th, 2017
- Author notification: January 15th, 2017
- Final version: April 15th, 2018
- Final notification: May 15th, 2018
- Publication: May 31st, 2018
Guest Editors
Heiko Paulheim (Data and Web Science Group, University of Mannheim. Web: http://www.heikopaulheim.com, Mail: heiko@informatik.uni-mannheim.de) is an assistant professor and interim chair of Data Science at
university of Mannheim. His research focus is at the crossroads of Semantic Web
and Linked Data on the one hand, and data mining and machine learning on the
other hand. Heiko is a co-author of more than 120 peer-reviewed papers
published in Semantic Web, artificial intelligence and machine learning
conferences and journals. He is an editorial board member of Web Intelligence
and Web Semantics, and has served as a PC member on conferences such ISWC,
ESWC, IJCAI, KI, AAAI, or Hypertext.
Volker Tresp (Siemens Corporate Technology and Ludwig Maximilian University of
Munich. Web: http://www.tresp.org/, Mail: Volker.Tresp@Siemens.com) is the head of a
research team in machine learning at Siemens, CorporateTechnology. He filed
more than 70 patent applications and was inventor of the year of Siemens in
1996. He has published more than 150 scientific articles and administered over
20 Ph.D. theses. His research focus in recent years has been „Machine Learning
in Information Networks“ for modelling Knowledge Graphs, medical decision
processes and sensor networks. In addition, he is exploring mathematical models
of the memory systems of the human brain. Since 2011 he is a Professor at the
Ludwig Maximilian University of Munich where he teaches an annual course on
Machine Learning.
Zhiyuan Liu (Natural Language
Processing Group, Tsinghua University. Web: http://nlp.csai.tsinghua.edu.cn/~lzy, Mail: liuzy@tsinghua.edu.cn) is an assistant professor at Tsinghua University. His research
focus is representation learning, knowledge graphs and social computation.
Zhiyuan has published more than 30 papers in leading conferences and journals
of AI and NLP including ACL, IJCAI and AAAI. He serves as Youth Associate
Editor of Frontiers of Computer Science, Area Chair of ACL, and PC members of
ACL, IJCAI, AAAI, etc.
Submission Guidelines
The Journal of Web Semantics solicits original scientific contributions of high quality. Following the overall mission of the journal, we emphasize the publication of papers that combine theories, methods and experiments from different subject areas in order to deliver innovative semantic methods and applications. The publication of large-scale experiments and their analysis is also encouraged to clearly illustrate scenarios and methods that introduce semantics into existing Web interfaces, contents and services.
Submission of your manuscript is welcome provided that it, or any translation of it, has not been copyrighted or published and is not being submitted for publication elsewhere. Manuscripts should be prepared for publication in accordance with instructions given in the JWS guide for authors. The submission and review process will be carried out using Elsevier's Web-based EES system. Please select “SI:Embeddings” when reaching the Article Type selection.
Submission of your manuscript is welcome provided that it, or any translation of it, has not been copyrighted or published and is not being submitted for publication elsewhere. Manuscripts should be prepared for publication in accordance with instructions given in the JWS guide for authors. The submission and review process will be carried out using Elsevier's Web-based EES system. Please select “SI:Embeddings” when reaching the Article Type selection.
Upon acceptance of an article, the author(s) will be asked to transfer copyright of the article to the publisher. This transfer will ensure the widest possible dissemination of information. Elsevier's liberal preprint policy permits authors and their institutions to host preprints on their web sites. Preprints of the articles will be made freely accessible on the JWS preprint server. Final copies of accepted publications will appear in print and at Elsevier's archival online server.