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-5 aims to bring together SW and DL research as well as industrial communities. SemDeep-5 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, collocation discovery and classification, or lexical entailment, to name only a few. 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 invite submissions on any approach combining Semantic Web technologies and Deep Learning and suggest the following topics.
The workshop will have a challenge (shared task) on evaluating contextualized word representations. The task is based on the WiC dataset (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. Training, development and test data will be provided for the participants. More information about the challenge and how to participate can be found at https://competitions.codalab.org/competitions/20010.
We invite three types of submissions:
All papers need to follow the ACL formatting guidelines. There is no space limit for references. Word and Latex templates available here: ACL_CfP
Please submit your papers via EasyChair, following this link
.