LINGUIST List 33.1827

Tue May 24 2022

Confs: Computational Linguistics/Japan

Editor for this issue: Everett Green <everettlinguistlist.org>



Date: 20-May-2022
From: Lukas Galke <Lukas.Galkempi.nl>
Subject: Machine Learning and the Evolution of Language (JCoLE 2022 Workshop)
E-mail this message to a friend

Machine Learning and the Evolution of Language (JCoLE 2022 Workshop)
Short Title: ml4evolang


Date: 05-Sep-2022 - 09-Sep-2022
Location: Kanazawa [and Online], Japan
Contact: Lukas Galke
Contact Email: < click here to access email >
Meeting URL: https://ml4evolang.github.io/

Linguistic Field(s): Computational Linguistics

Meeting Description:

We are pleased to announce the workshop ''Machine Learning and the Evolution of Language: Building a bridge between communities'', which will be held at JCoLE 2022 (Japan and online, September 5th - 8th, 2022). The workshop will take place on September 5th, 2022 over two sessions (morning and afternoon, Japan time).

In the past three decades, numerous studies have attempted to mimic the evolution of language with human participants and agent-based computational models. Meanwhile, in the last decade, the machine learning community has similarly made exciting strides in simulating emergent communication with deep and reinforcement learning methods.

Although both areas of research have similar interests and work on similar questions, there has been little crosstalk between them so far. This is unfortunate, since the progress in machine learning and other areas of AI may allow language evolution researchers to model phenomena that they could not model before. At the same time, theoretical and experimental knowledge of language evolution coming from the linguistics community may help focus models of emergent communication used by the machine learning community.

The goal of this workshop is therefore to relate these two areas by bringing together researchers from both backgrounds, establishing common ground, bootstrapping a mutual dialogue between them, and discussing the potential pitfalls of incorporating machine learning methods in the study of language evolution.

Program:

Schedule:
https://ml4evolang.github.io/#schedule

The workshop will feature presentations from invited speakers and a lively panel discussion on the advantages and pitfalls of using emergent communication with deep learning models as well as more classic agent-based computational models.

Invited speakers are:

Rahma Chaabouni (DeepMind)
Katie Mudd (AI Lab, Vrije Universiteit Brussel)
Matt Spike (University of Edinburgh)
Douwe Kiela (Huggingface)

For more information on the workshop schedule, please visit: https://ml4evolang.github.io/

Organizers:
- Mathieu Rita -- PhD student at INRIA
- Lukas Galke -- Postdoctoral researcher, Max Planck Institute for Psycholinguistics
- Dr. Florian Strub -- Senior Researcher, DeepMind
- Prof. Olivier Pietquin -- Research Lead - Google Brain
- Prof. Emmanuel Dupoux -- Professor - EHESS / Senior Researcher - Meta AI Research
- Prof. Bart de Boer -- Senior Researcher, Artificial Intelligence Lab, Vrije Universiteit Brussel
- Dr. Limor Raviv -- Group Leader, Max Planck Institute for Psycholinguistics




Page Updated: 24-May-2022