*** DeeLIO - First Call for Papers ***
Deep Learning Inside Out (DeeLIO) The Second Workshop on Knowledge Extraction and Integration for Deep Learning Architectures
Collocated with NAACL 2021 in Mexico City, Mexico or online
* Workshop description *
The second edition of the DeeLIO workshop will be collocated with NAACL 2021. The first edition of DeeLIO has been a satellite workshop of the online EMNLP 2020 conference.
The central theme of the workshop remains the knowledge extraction and integration for deep learning architectures. Following the success of deep learning methods in NLP, the focus of the workshop is on exploring the linguistic, symbolic, and real-world knowledge that can be extracted from deep learning models, and to identify potentially useful sources of language-related information that can be integrated and make the models “smarter” and more effective in natural language understanding tasks.
The Deep Learning Inside Out (DeeLIO) workshop aims precisely 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 networks encode, the extent to which this can be used for building resources, and whether this knowledge can be beneficial by being re-integrated in the models, compared to external hand-crafted knowledge.
We especially encourage works on structurally diverse languages with varying semantic-syntactic properties and in low-data regimes. We hope that DeeLIO will 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. We also hope to inspire new work that will analyze the difference in knowledge that can be extracted across different 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 in different languages using deep learning models; * (re)integration of (semi-)automatically compiled resources into deep learning models; * using external knowledge in low-resource languages through transfer techniques or joint multilingual modelling.
We are delighted to announce our three keynote speakers at DeeLIO 2021:
Lena Voita - University of Edinburgh and University of Amsterdam Vered Shwartz - Allen Institute for AI (AI2) and University of Washington Sebastian Riedel - Facebook AI Research (FAIR)
* Submission *
We invite the submission of long and short papers on original and unpublished research in any topic related to 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.
Papers should follow the official NAACL 2021 style guidelines.
Paper submission is electronic, using the START conference management system:
Double submission of papers will need to be notified at submission.
The DeeLIO workshop will be collocated with NAACL 2021 in Mexico City, Mexico or online.
* Important Dates *
• March 15, 2021: Workshop Paper Due Date
• April 15, 2021: Notification of Acceptance
• April 30, 2021: Camera-ready papers due
• June 10, 2021: Workshop
Note: All deadlines are 11:59PM (UTC-12:00 / Anywhere on Earth).
* Workshop Chairs *
Eneko Agirre (University of the Basque Country) Marianna Apidianaki (University of Helsinki) Ivan Vulić (University of Cambridge)