Image by O'Reilly

6th Workshop on Semantic Deep Learning (SemDeep-6)

A workshop and challenge, to be held virtually in January 2021, co-located with IJCAI-PRICAI 2020. Japan, January 2021

Previous editions: SemDeep-1@ESWC 2017, SemDeep-2@IWCS 2017, SemDeep-3@COLING 2018, SemDeep-4@ISWC 2018, SemDeep-5@IJCAI 2019

Proceedings

SemDeep-6 proceedings are now online as ACL Anthology.

Workshop Description

This 6th Workshop on Semantic Deep Learning (SemDeep-6) aims at bringing together Semantic Web and Deep Learning research as well as industrial communities. Semantic Web technologies and Deep Learning share the goal of creating intelligent artifacts that emulate human capacities such as reasoning, validating, and predicting, and at the same time are central to knowledge representation, either data driven or rule-based. Despite these similarities and the obvious connection between them, there exist as of today few venues where this interplay is explicitly explored. To bridge this gap, SemDeep addresses the open research question of how Semantic Web technologies can be united with state-of-the-art machine learning approaches. In contrast to previous editions, our focus in this edition will be on how joining Samntic Web and Deep Learning research can contribute to Explainable Artificial Intelligence (XAI).

Given the success of the Word-in-Context (WiC) challenge collocated with SemDeep-5, we will continue this collaboration and SemDeep-6 will be joined by WiC-TSV (Target Sense Verification for Words in Context), which will extend the WiC dataset in several ways, such as hypernyms and definitions as well as two domain-specific datasets.

Topics of interest:

This full day workshop suggests the following topics of interest:

  • Explainable Artificial Intelligence (XAI)
    • joint Semantic Web and Deep Learning approaches to foster XAI
  • Structured knowledge in deep learning
    • neural networks and logic rules for semantic compositionality
    • learning and applying knowledge graph embeddings
    • learning semantic similarity and encoding distances as knowledge graph
    • ontology-based text classification
    • multilingual resources for neural representations of linguistics
  • Reasoning and inferences and deep learning
    • commonsense reasoning and vector space models
    • reasoning with deep learning methods
  • Learning knowledge representations with deep learning
    • deep learning methods for knowledge-base completion
    • deep ontology learning
    • deep learning models for learning knowledge representations from text
    • deep learning ontological annotations
    • Application-specific combinations:
      • Deep Learning, Semantic Web, and natural language
      • Deep Learning, Semantic Web, and computer vision
      • Deep Learning, Semantic Web, and domain-specific applications