Deep learning and neural network approaches are indispensable in modern Natural Language Processing and generally in all kinds of linguistic data analysis approaches. Artificial intelligence integrating knowledge is one of the core topics in the current research which focuses on providing human thinking for AI to solve complex tasks. One of the important techniques for supporting this research is knowledge acquisition or so-called relation extraction. Relation extraction and deep learning can serve the understanding of the specificities of linguistic data, to be better exploited and combined with linked data mechanisms. Knowledge is a way of understanding the world, aiming to provide a human-level cognition and intelligence for the next-generation artificial intelligence. One way of knowledge representation is semantic relations between entities. Relation Extraction ensures an effective way to automatically acquire important knowledge of semantic relations. It is a sub-task of information extraction and plays an essential role in Natural Language Processing. Its purpose is to identify semantic relations between entities from natural language text. Concerning the current research, there is a field of studies for relation extraction which have described the techniques based on Deep Neural Networks used as a prevailing technique in the research. The workshop intends to be an event of discussion for researchers interested in addressing the peculiarities of the aforementioned interrelated research areas and in advancing the state of the art in deep learning, relation extraction, and linguistic data science.
The workshop topics are the following (but not limited to):
● Deep Learning for Linguistic Linked (Open) Data, modelling, resources & interlinking
● LLOD and Deep Learning for Digital Humanities
● Enhancement of language models with structured linguistic data
● Use cases combining language models and structured linguistic data
● Deep Learning and LLOD in NLP
● Deep learning and relation extraction
● Deep learning and knowledge graphs
● Multilingual data preparation for the BATS experiment