Click to go to Gather

There are four colocated workshops with IWCS, that take place mostly in parallel on the 16th of June. Most of their program takes place on Zoom, but these sessions are all available through our Gather as well. Since only paying participants have access, we cannot link directly to the Zoom meetings, but you can find these links in your email. This should make it more convenient to visit multiple workshops. Specific programs are available on the linked websites.

The IWCS proceedings are available for online browsing and download. The workshop proceedings are available here. The proceedings are made available for convenience before they appear on the aclanthology.

Time (CET) Activity Where?
16 June - Workshops
13:00 - 16:00 ISA-17 Day 1 Zoom
14:00 - 20:00 SemSpace 2021 Zoom
14:30 - 20:00 NALOMA'21 Zoom
16:00 - 20:00 MMSR I Zoom & Gather (MMSR I)
20:00 - 20:30 IWCS 2021 Welcome Zoom

17 June - IWCS Day 1
12:00 - 15:00 ISA-17 Day 2 Zoom
15:00 - 16:00 Keynote 1: Mirella Lapata
The Democratization of Semantic Parsing via Zero-Shot Cross-lingual Learning
Note: at the end, we will watch the teaser videos of Session 1 together
16:00 - 17:00 Main session 1 - see below for details Gather (Posters)
17:00 - 18:00 Open space (unconferencing) - explanation below Gather (Open Space)
18:00 - 19:00 Semantic surprise event - explanation below Gather (Surprise Event)

18 June - IWCS Day 2
15:00 - 16:00 Keynote 2: Rachel Rudinger
When Pigs Fly and Birds Don't: Exploring Defeasible Inference in Natural Language
Note: at the end, we will watch the teaser videos of Session 2 together
16:00 - 17:15 Main session 2 - see below for details Gather (Posters)
17:15 - 18:00 The Future of Computational Semantics - explanation below Gather (Future of CompSem)
18:00 - 18:30 Ending ceremony (including outstanding paper awards!) Zoom

Open Space (unconferencing) - Day 1 at 17:00 CET (Gather)

This session is based on the Open Space workshop at IWCS 2013 and is similar to the "Birds of a Feather" sessions at *ACL conferences. The idea is to allow participants to discuss any topic in computational semantics they are passionate about, in small groups of people who care about the same topic. There is a separate room for this in Gather, follow the instructions on the floor to locate it. In the room, simply find your favorite topic and join the table. You can join any meeting you like, and are also free to leave meetings to see what's going on at different ones. Each table will have a designated chair/moderator and a shared whiteboard to facilitate the discussion. Have fun!

Semantic Surprise Event - Day 1 at 18:00 CET (Gather)

Surprise! We will organize a fun, short quiz. A few questions will be related to IWCS, but most of it will be general knowledge, so everybody can have a good time. This is meant as the main social event. Participation is done in teams, but there is no need to form a team in advance, the room will have instructions on how to create them. So, yes, you can just join individually and perhaps meet some new people! There is a separate Gather room for this session, follow the instructions on the floor to locate it. The room has clear instructions on how to participate, so don't worry if it's not all clear to you now. We hope to see you there!

The Future of Computational Semantics - Day 2 at 17:15 (Gather)

This session will be a panel! The panel discussion will be kicked off by Harry Bunt, Katrin Erk and Martha Palmer. But there's a twist: the panel members are not fixed! Everybody in the audience is allowed to join, at which point one of the current panel members has to leave. Just stand in line, so the chair of the session knows to let you in. Hopefully, this will lead to a diverse discussion, in which everybody can get their voice heard. Again, there's a separate Gather room for this, which contains clear instructions on how to participate.

The panel will start off by discussing the following. Large language models used in neural network systems show good performance. Are we done with symbolic representations? Do we still need semantically annotated corpora? Or are there components missing to ensure explainability, switching to new domains, or multi-modal meanings? What are the next steps we should take?

Some practical things: panel members stand on a "spotlight" tile, meaning they can address the whole room, but they cannot hear people in the audience. So it's okay to watch the panel in a small group and talk about it at the same time, you will not disturb them! In Gather, it's clear what seats are for groups and what seats are for individuals. You can also use Gather chat if you're not comfortable joining the panel, the moderator will pay attention to that.

Main Session 1

#1: CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts
Maria Becker, Katharina Korfhage, Debjit Paul and Anette Frank [PDF] [Video]

#2: Computing All Quantifier Scopes with CCG
Miloš Stanojević and Mark Steedman [PDF] [Video]

#3: Encoding Abstractive Knowledge Transitivity for Zero-shot Science Question Answering
Zili Zhou, Marco Valentino, Donal Landers and André Freitas [PDF] [Video]

#4: Critical Thinking for Language Models
Gregor Betz, Christian Voigt and Kyle Richardson [PDF] [Video]

#5: Looking for a Role for Word Embeddings in Eye-Tracking Features Prediction: Does Semantic Similarity Help?
Lavinia Salicchi, Alessandro Lenci and Emmanuele Chersoni [PDF] [Video]

#6: Monotonicity Marking from Universal Dependency Trees
Zeming Chen and Qiyue Gao [PDF] [Video]

#7: Is that really a question? Going beyond factoid questions in NLP
Aikaterini-Lida Kalouli, Rebecca Kehlbeck, Rita Sevastjanova, Oliver Deussen, Daniel Keim and Miriam Butt [PDF] [Video]

#8: Breeding Fillmore’s Chickens and Hatching the Eggs: Recombining Frames and Roles in Frame-Semantic Parsing
Gosse Minnema and Malvina Nissim [PDF] [Video]

#9: Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning
Bill Noble and Vladislav Maraev [PDF] [Video]

#10: Builder, we have done it: Evaluating & Extending Dialogue-AMR NLU Pipeline for Two Collaborative Domains
Claire Bonial, Mitchell Abrams, David Traum and Clare Voss [PDF] [Video]

#11: Variation in framing as a function of temporal reporting distance
Levi Remijnse, Marten Postma and Piek Vossen [PDF] [Video]

#12: Automatic Classification of Attributes in German Adjective-Noun Phrases
Neele Falk, Yana Strakatova, Eva Huber and Erhard Hinrichs [PDF] [Video]

Main Session 2

#1: Switching Contexts: Transportability Measures for NLP
Guy Marshall, Mokanarangan Thayaparan, Philip Osborne and André Freitas [PDF] [Video]

#2: Applied Temporal Analysis: A Complete Run of the FraCaS Test Suite
Jean-Philippe Bernardy and Stergios Chatzikyriakidis [PDF] [Video]

#3: Predicate Representations and Polysemy in VerbNet Semantic Parsing
James Gung and Martha Palmer [PDF] [Video]

#4: Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards
Marco Valentino, Ian Pratt-Hartmann and André Freitas [PDF] [Video]

#5: Automatic Assignment of Semantic Frames in Disaster Response Team Communication Dialogues
Natalia Skachkova and Ivana Kruijff-Korbayova [PDF] [Video]

#6: Implicit representations of event properties within contextual language models: Searching for "causativity neurons"
Esther Seyffarth, Younes Samih, Laura Kallmeyer and Hassan Sajjad [PDF] [Video]

#7: New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger To the Voice Assistant Domain
Touhidul Alam, Alessandra Zarcone and Sebastian Padó [PDF] [Video]

#8: A Transition-based Parser for Unscoped Episodic Logical Forms
Gene Kim, Viet Duong, Xin Lu and Lenhart Schubert [PDF] [Video]

#9: "Politeness, you simpleton!" retorted [MASK]: Masked prediction of literary characters
Eric Holgate and Katrin Erk [PDF] [Video]

#10: Tuning Deep Active Learning for Semantic Role Labeling
Skatje Myers and Martha Palmer [PDF] [Video]

#11: SemLink 2.0: Chasing Lexical Resources
Kevin Stowe, Jenette Preciado, Kathryn Conger, Susan Windisch Brown, Ghazaleh Kazeminejad and Martha Palmer [PDF] [Video]