5th Workshop on Semantic Deep Learning (SemDeep-5)

A workshop and challenge co-located with IJCAI 2019 in Macau, China

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

Image by O'Reilly

Proceedings

SemDeep-5 proceedings are now online as ACL Anthology.

Workshop Description

We describe in this submission our proposal for a fifth edition of the workshop on Semantic Deep Learning (SemDeep-5). As its past editions, this workshop aims at bringing together Semantic Web and Deep Learning research as well as industrial communities. Additionally, the fifth edition of the workshop offers a platform for joining computational linguistics and formal approaches to represent information and knowledge, and so opens the discussion for new and innovative application scenarios for computational linguistics. The workshop will also contribute to widening the appeal of IJCAI to audiences outside of computational linguistic research as it is based on a joint call of structured knowledge and state-of-the-art language processing approaches.

In contrast to previous editions, we intend to join forces with a shared task for SemDeep-5 that will ask for the submission and presentation of practical applications in the domain of evaluating meaning representations. This shared task provides a joint task of semantic structure in the organization of senses and their transformation to embeddings, which are highly useful for word sense disambiguation, entity linking, and semantic search.

Participate in our challenge on Word-in-Context (WiC)!

This workshop will take place on 12 August 2019 from 14:00 to 18:00, Room Sicily 2405, Venetian Macao Resort Hotel, Macao, China. Please see program tab for accepted papers.

Topics of interest:

This full day workshop suggests the following topics of interest:

  • Structured knowledge in deep learning
    • neural networks and logic rules for semantic compositionality
    • learning and applying knowledge graph embeddings to NLP tasks
    • learning semantic similarity and encoding distances as knowledge graph
    • ontology-based text classification
    • multilingual resources for neural representations of linguistics
    • semantic role labeling
  • 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