*** DeeLIO - First Call for Papers ***
Deep Learning Inside Out (DeeLIO) The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures https://sites.google.com/view/deelio-ws/
Collocated with EMNLP 2020 in Punta Cana, Dominican Republic.
Deep learning methods have opened up a new era in NLP, providing the community with extremely powerful tools and language representations, and reaching impressive performance in numerous tasks. After the first enthusiasm this success stirred, the community started looking inside the box to understand what is coded in there, but also outside of the same (neural) box, seeking other potentially useful sources of language-related information. Deep Learning Inside Out (DeeLIO) is the first workshop on knowledge extraction and integration for deep learning architectures. It aims to bring together the knowledge interpretation, extraction and integration lines of research in deep learning, and cover the area in between. It will explore the introduction of external knowledge in deep learning models and representations, the types of linguistic and real-world knowledge neural nets encode, the extent to which this can be used for building resources, and whether this knowledge can be beneficial to them by being re-integrated in the models, compared to external hand-crafted knowledge. DeeLIO also has a strong focus on structurally diverse languages with varying semantic-syntactic properties and low-data regimes. The workshop’s aim is to inspire novel variation-aware transfer learning and multilingual solutions on how to use the knowledge from resource-rich languages to inform deep learning architectures where external repositories are scarce or missing. The focus is on lexico-semantic knowledge that can be recovered from, or integrated into, deep learning methods across a variety of languages.
Topics of interest include but are not limited to:
* integration of external knowledge in neural networks (under the form of semantic specialization of embeddings, retrofitting, joint modeling, or other); * exploration of the types of linguistic and world knowledge neural models, architectures and representations encode; * extraction of linguistic and world knowledge from deep learning models; * use of the knowledge extracted from deep learning models in practice (for resource enrichment, knowledge transfer to resource-lean languages, or other); * analysing and understanding the limitations of the knowledge about language and the world acquired by current neural models; * probing and analysing different types of hand-crafted knowledge that can enhance “blind” distributional models; * benefits of using external versus internally encoded knowledge, and their combination, for knowledge enhancement in neural networks; * development and enrichment of lexico-semantic knowledge resources using deep learning models; * (re)integration of (semi-)automatically compiled resources into deep learning models; * using external knowledge in resource-lean languages through transfer techniques or joint multilingual modelling.
We invite the submission of long and short papers on original and unpublished research in any topic related with knowledge interpretation and integration in deep neural networks. Long papers may consist of up to 8 pages of content + references. Short papers may consist of up to 4 pages of content + references. Upon acceptance, both types of papers will be given one additional page of content. Authors are encouraged to use this additional page for addressing reviewers’ comments in the final version.
Paper submission is electronic, using the Softconf START conference management system. Paper template files will be provided soon on the workshop website.
Double submission of papers will need to be notified at submission.
The DeeLIO workshop will be collocated with EMNLP 2020 in Punta Cana, Dominican Republic.
• Deadline for submission: July 15, 2020
• Notification of Acceptance: August 17, 2020
• Camera-ready papers due: August 31, 2020
• Workshop: November 11 or 12, 2020
Note: All deadlines are 11:59PM UTC-12:00.
Eneko Agirre (University of the Basque Country) Marianna Apidianaki (University of Helsinki) Ivan Vulić (University of Cambridge)