- From: Koutraki, Maria (AIFB) <maria.koutraki@kit.edu>
- Date: Sun, 4 Mar 2018 17:14:02 +0000
- To: "semantic-web@w3.org" <semantic-web@w3.org>
- Message-ID: <1520183642207.75727@kit.edu>
*Apologies for cross-posting* --------------------------------------------------------------------------------- Call For Papers --------------------------------------------------------------------------------- 1st International Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies (DL4KGS) http://usc-isi-i2.github.io/DL4KGS/ In conjunction with ESWC 2018, 3rd-7th June 2018, Heraklion, Crete, Greece --------------------------------------------------------------------------------- Workshop Overview --------------------------------------------------------------------------------- Semantic Web technologies and deep learning share the goal of creating intelligent artifacts that emulate human capacities such as reasoning, validating, and predicting. There are notable examples of contributions leveraging either deep neural architectures or distributed representations learned via deep neural networks in the broad area of Semantic Web technologies. Knowledge Graphs (KG) are one of the most well-known outcomes from the Semantic Web community, with wide use in web search, text classification, entity linking etc. KGs are large networks of real-world entities described in terms of their semantic types and their relationships to each other. A challenging but paramount task for problems ranging from entity classification to entity recommendation or entity linking is that of learning features representing entities in the knowledge graph (building “knowledge graph embeddings”) that can be fed into machine learning algorithms. The feature learning process ought to be able to effectively capture the relational structure of the graph (i.e. connectivity patterns) as well as the semantics of its properties and classes, either in an unsupervised way and/or in a supervised way to optimize a downstream prediction task. In the past years, Deep Learning (DL) algorithms have been used to learn features from knowledge graphs, resulting in enhancements of the state-of-the-art in entity relatedness measures, entity recommendation systems and entity classification. DL algorithms have equally been applied to classic problems in semantic applications, such as (semi-automated) ontology learning, ontology alignment, duplicate recognition, ontology prediction, relation extraction, and semantically grounded inference. --------------------------------------------------------------------------------- Topics of Interest --------------------------------------------------------------------------------- Topics of interest for this first workshop on Deep Learning for Knowledge Graphs and Semantic Technologies, include but are not limited to the following fields and problems: Knowledge graph embeddings for entity linking, recommendation, relatedness Knowledge graph embeddings for link prediction and validation Time-aware and scalable knowledge graph embeddings Text-based entity embeddings vs knowledge graph entity embeddings Deep learning models for learning knowledge representations from text Knowledge graph agnostic embeddings Knowledge Base Completion Type Inference Question Answering Domain Specific Knowledge Base Construction Reasoning over KGs and with deep learning methods Neural networks and logic rules for semantic compositionality Quality checking and Data cleaning Multilingual resources for neural representations of linguistics Commonsense reasoning and vector space models Deep ontology learning Deep learning ontological annotations Applications of knowledge graph embeddings in real business scenarios ------------------------------------------------------------------------------------ Important Dates ------------------------------------------------------------------------------------ Submission deadline: Friday March 16, 2018 Notification of Acceptance: Tuesday April 17, 2018 Camera-ready Submission: Tuesday April 24, 2018 --------------------------------------------------------------------------------- WORKSHOP CO-CHAIRS --------------------------------------------------------------------------------- Michael Cochez, Fraunhofer Institute for Applied Information Technology, Germany Thierry Declerck, DFKI GmbH, Germany Gerard de Melo, Rutgers University, USA Luis Espinosa Anke, Cardiff University, UK Besnik Fetahu, L3S Research Center, Leibniz University of Hannover, Germany Dagmar Gromann, Technical University Dresden, Germany Mayank Kejriwal, Information Sciences Institute, USA Maria Koutraki, FIZ-Karlsruhe, Karlsruhe Institute of Technology (KIT), Germany Freddy Lecue, Accenture Technology Labs, Ireland; INRIA, France Enrico Palumbo, ISMB, Italy; EURECOM, France; Politecnico di Torino, Italy Harald Sack, FIZ Karlsruhe, Karlsruhe Institute of Technology (KIT), Germany More information about DL4KGs 2018 is available at: http://usc-isi-i2.github.io/DL4KGS/
Received on Sunday, 4 March 2018 17:14:42 UTC