Call for Papers

With the experiences gained from two previous workshops on Semantic Deep Learning, we would like to take this endeavor one step further by providing a platform at COLING 2018 where researchers and professionals in computational linguistics are invited to report results and systems on the possible contributions of Deep Learning to classic problems in semantic applications, such as meaning representation, dependency parsing, semantic role labelling, word sense disambiguation, semantic relation extraction, statistical relational learning, knowledge base completion, or semantically grounded inference.

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. These include, among others: (lightweight) ontology learning, ontology alignment , ontology annotation, and ontology prediction. Ontologies, on the other hand, have been repeatedly utilized as background knowledge for machine learning tasks. As an example, there is a myriad of hybrid approaches for learning embeddings by jointly incorporating corpus-based evidence and semantic resources. This interplay between structured knowledge and corpus-based approaches has given way to knowledge-rich embeddings, which in turn have proven useful for tasks such as hypernym discovery , collocation discovery and classification, word sense disambiguation, and many others.

We thus invite submissions that illustrate how NLP can benefit from the interaction between deep learning and Semantic Web resources and technologies. At the same time, we are interested in submissions that show how knowledge representation can assist in deep learning tasks deployed in the field of NLP and how knowledge representation systems can build on top of deep learning results, for example in the field of Neural Machine Translation (NMT).