28.08.2020
LANTERN Workshop at COLING 2020: Extended Deadlines!
The workshop is organised by Aditya Mogadala (project B4) and will take place on December 13, 2020 in Barcelona, Spain.
Workshop website: https://www.lantern.uni-saarland.de/2020/
——————————————
ABOUT THE WORKSHOP
——————————————
LANTERN: The Second Workshop Beyond Vision and LANguage: InTEgrating Real World KNowledge
Language is acquired, used, and evaluated by understanding the world around us. It is thus essential to capture such an understanding by exploiting knowledge from sources that are useful for grounding language. Recent work showed the potential of visually-grounded language in addressing task-specific challenges (e.g., visual captioning, VQA, dialog, etc.). In this workshop, we aim to go beyond the task-specific integration of language and vision, and encourage submissions that leverage knowledge from external sources that are either provided by an environment or some fixed knowledge.
Our motto: When you are groping in the dark, knowledge gives you the light!
——————————————
TOPICS OF INTEREST
——————————————
Topics of interest include, but are not limited to:
- Application of language and vision to robotics
- Cognitively- and neuroscience-driven vision and language learning (eye-tracking, fMRI, etc.)
- Common-sense knowledge acquisition from vision
- Enhancing visual perception with language and structured knowledge
- Human-robot interaction with language understanding and visual perception
- Integration of vision and language by building cross-modal relationship networks
- Integrated models of real-world knowledge, vision, and language for generating context-sensitive embeddings
- Language and vision for learning games
- Learning of quantities from vision
- Multi-task learning for integration of language and vision
- Reasoning with language to improve visual perception
- Text-to-Image (natural, sketch, synthetic) generation with external knowledge
- Theoretical understanding of limitations in the integration of vision and language
- Visual dialog, captioning and Q&A by incorporating common-sense/real-world knowledge
- Other novel tasks which combine language and vision with means of external knowledge
——————————————
IMPORTANT DATES
——————————————
Deadline for submission: September 11, 2020 [Extended Deadline]
Notification of acceptance: October 07, 2020 [Extended Deadline]
Deadline for camera-ready version: October 16, 2020 [Extended Deadline]
Workshop date: December 13, 2020
All deadlines are calculated at 11:59pm Pacific Daylight Savings Time (UTC – 12h)
——————————————
INVITED SPEAKERS
——————————————
Yonatan Bisk, Microsoft Research & CMU
Gemma Boleda, Universitat Pompeu Fabra & ICREA
Angeliki Lazaridou, DeepMind
Stefan Lee, Oregon State University
———————————————–
SUBMISSION INSTRUCTIONS
———————————————–
We solicit two categories of papers: long and short workshop papers that will be included in the workshop proceedings as archival publications. All submissions should be in PDF format and made through the Softconf link (https://www.softconf.com/coling2020/LANTERN/)
Submissions will go through a double-blind review process, where each submission is reviewed by at-least two program committee members. Accepted papers will be presented by the authors in a regular workshop session either as a talk or a poster.
All submissions must be written in English and follow the COLING 2020 formatting requirements using either Word or LaTeX template files provided by COLING 2020 (https://coling2020.org/).
- Long paper submission: up to 9 pages of content, plus bibliography
- Short paper submission: up to 4 pages of content, plus bibliography
——————————————
SPONSORS
——————————————
SFB 1102 (http://www.sfb1102.uni-saarland.de/)
Hugging Face (https://huggingface.co/) [Best Papers]
————————————-
CONTACTS
————————————-
The co-chairs of the workshop can be contacted by email at: lantern2019@googlegroups.com
——————————————
ORGANIZING COMMITTEE
——————————————
Aditya Mogadala, Saarland University
Sandro Pezzelle, University of Amsterdam
Dietrich Klakow, Saarland University
Marie-Francine Moens, KU Leuven
Zeynep Akata, University of Tübingen