Workshop

LANTERN 2021

The Third Workshop Beyond Vision and LANguage:
inTEgrating Real-world kNowledge

EACL 2021 Workshop
April 20, 2021
virtual

Schedule

Day: Tuesday, 20 April, 2021
Start: 11:30 CEST, End: 18:30 CEST
Location: Virtual


Interaction
  • Links to Zoom and Rocket.Chat on the virtual conference page: https://www.virtual2021.eacl.org/workshop_WS-11.html
  • Twitter: #LANTERN
  • Break-out session for discussion in Workshop Room 4 -> Poster Room 4 (15:45 - 16:45 CEST)
  • Mails to the organizers: lantern2021 (at) googlegroups (dot) com

Time Table
  • Welcome and Opening Remarks
    11:30 – 11:45

  • Invited Talk: Sebastian Riedel (UCL and Facebook AI Research)
    Probably Asked Questions and Parametric vs Non-Parametric Knowledge
    11:45 – 12:30

  • Invited Talk: Aida Nematzadeh (Deep Mind)
    Learning language by observing the world and learning about the world from language
    12:30 – 13:15

  • Contributed Talks 1
    13:15 – 13:45
    1. Sreyasi Nag Chowdhury, Rajarshi Bhowmik, Hareesh Ravi, Gerard de Melo, Simon Razniewski and Gerhard Weikum
      EXPLOITING IMAGE–TEXT SYNERGY FOR CONTEXTUAL IMAGE CAPTIONING
    2. Sebastian Bujwid and Josephine Sullivan
      LARGE-SCALE ZERO-SHOT IMAGE CLASSIFICATION FROM RICH AND DIVERSE TEXTUAL DESCRIPTIONS

  • Lunch Break
    13:45 – 15:00

  • Contributed Talks 2
    15:00 – 15:45
    1. Violetta Shevchenko, Damien Teney, Anthony Dick and Anton van den Hengel
      REASONING OVER VISION AND LANGUAGE: EXPLORING THE BENEFITS OF SUPPLEMENTAL KNOWLEDGE
    2. Damien Sileo
      VISUAL GROUNDING STRATEGIES FOR TEXT-ONLY NATURAL LANGUAGE PROCESSING
    3. Ronja Utescher and Sina Zarrieß
      WHAT DID THIS CASTLE LOOK LIKE BEFORE? EXPLORING REFERENTIAL RELATIONS IN NATURALLY OCCURRING MULTIMODAL TEXTS

  • Break-Out Session in Gather.Town for Discussion
    15:45 – 16:45
    Workshop Room 4 -> Poster Room 4

  • Invited Talk: Brenden Lake (NYU and Facebook AI Research)
    Building machines that understand words as people do
    16:45 – 17:30

  • Invited Talk: Danna Gurari (University of Texas at Austin)
    Vision and Language Problems for a Real-World Application of Describing Images Taken by People Who Are Blind
    17:30 – 18:15

  • Best Paper Award + Closing Remarks
    18:15 – 18:30