In our LangSci Colloquium on November 12th 2020, Frank Seifart from Leibniz-Centre General Linguistics (ZAS)  will talk about „Studying speech rate cross-linguistically: Resource building and case studies on final lengthening and pause probabilities“.

Please contact us if you are interested in joining the Zoom Meeting!

We are very proud to announce that Iona Gessinger and Eran Raveh (Project C1) received a best student paper award at Interspeech 2020. Many Congratulations to both of you!

Read the full paper on „Phonetic accommodation of L2 German speakers to the virtual language learning tutor Mirabella“ here.

After a long break, we can finally reactivate our LangSci Colloquium Series and are excited to announce the first virtual talk in Winter Semester 2020/2021!

Oliver Bott will talk on October 29th 2020 about Implicit Causality and Explicit Consequentiality.

Please contact us if you are interested in joining the Zoom Meeting.

Congratulations to the accepted presentation on „The effect of predictability on the duration of phrase-final syllables“ that will be given by Bistra Andreeva, Bernd Möbius, Omnia Ibrahim and Ivan Yuen (Project C1) at the workshop “Prosodic boundary phenomena” to take place at the 43rd annual conference of the German Linguistic Society (Deutsche Gesellschaft für Sprachwissenschaft, DGfS).

We are very pleased to announce the papers accepted for Coling2020

CONGRATULATIONS TO ALL AUTHORS!

---

Zhai, Fangzhou; Demberg, Vera; Koller, Alexander: Story Generation with Rich Details  – Project A3 – 

Köhn, Arne; Wichlacz, Julia; Torralba, Álvaro; Höller, Daniel; Hoffmann, Jörg; Koller, Alexander: Generating Instructions at Different Levels of Abstraction  – Project A7 –

Chowdhury, Koel Dutta; España-Bonet, Cristina; van Genabith, Josef: Understanding Translationese in Multi-view Embedding Spaces – Project  B6 –

Mosbach, Marius; Degaetano-Ortlieb, Stefania; Krielke, Marie-Pauline; Abdullah, Badr; Klakow, Dietrich: A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English – Projects B1, C4, B4 –

A new article by members of project A1 entitled „Splitting event‐related potentials: Modeling latent components using regression‐based waveform estimation“ has been published in the European Journal of Neuroscience.

Read the full article here.

A new journal article by the members of project B1 entitled „Linguistic Variation and Change in 250 years of English Scientific Writing: A Data-driven Approach“ has been published in Frontiers in Artificial Intelligence.

You can access the full article here.

Congratulations to our PI Vera Demberg who has been awareded with a 1.5 million euro grant over 5 years from the European Research Council. The aim of the research project is to improve human-machine communication by reducing misunderstandings and ensuring that people can communicate with computers more naturally.

Get more information on her current work and read the full article here.

Barcelona, Spain — December 13, 2020
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: August 21, 2020
Notification of acceptance:  September 24, 2020
Deadline for camera-ready version: October 11, 2020
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

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