Semantic Web (SW) technologies and Deep Learning (DL) share the goal of creating intelligent artifacts. Both disciplines have had a remarkable impact in data and knowledge analysis, as well as knowledge representation, and in fact constitute two complementary directions for modeling linguistic phenomena and solving semantically complex problems. In this context, and following the main foundations set in past editions, SemDeep-6 aims to bring together SW and DL research as well as industrial communities.
SemDeep-6 is interested in contributions of DL to classic problems in semantic applications, such as: (semi-automated) ontology learning, ontology alignment, ontology annotation, duplicate recognition, ontology prediction, knowledge base completion, relation extraction, and semantically grounded inference, among many others. At the same time, we invite contributions that analyse the interaction of SW technologies and resources with DL architectures, such as knowledge-based embeddings, lexical entailment, relation classification or knowledge base completion. This year we are particularly interested in how this combination can contribute to the bigger field of Explainable AI. This workshop seeks to provide an invigorating environment where semantically challenging problems which appeal to both Semantic Web and Computational Linguistic communities are addressed and discussed.
We are happy to announce that Michael Spranger, a researcher at Sony Computer Science Laboratories Inc. in Tokyo, Japan, who has been actively contributing to neural-symbolic learning and reasoning, has agreed to give a keynote at SemDeep-6.
We invite submissions on any approach combining Semantic Web technologies and Deep Learning and suggest the following topics.
The workshop includes a challenge (shared task) on Word-in-Context Target Sense Verification (WiC-TSV). Training, development and test data is provided for all participants. All the information can be found in the CodaLab website.
The task is based on an extended WiC-TSV (Target Sense Verification for Words in Context) dataset (Last year's dataset can be found at https://pilehvar.github.io/wic/, NAACL 2019) and targets different areas of lexical semantics including, but not limited to, sense representation, word sense disambiguation, and contextualised word embeddings.
We invite three types of submissions:
All papers need to follow the ACL formatting guidelines. Templates are available from the ACL website. No page limit for references for all types of submission.
Please submit your papers via EasyChair, following this link..