Track / Overview

The AI & Language track includes researchers and engineers at top tech companies, research groups and startups using machine learning for language tasks and features four major themes.

Representations, interpretability & visualisation

Representations and interpretability are especially challenging for language tasks because language is sparse and, unlike with vision, there are no inherently visualisable intermediate representations. Representations, interpretability, evaluation and confidence are intriguing open research questions.

Engineering & Tools

The tools and datasets for building and deploying natural language processing systems are evolving, while online learning pipelines introduce new demands. We will hear from engineering teams behind highly scaled systems on their stacks and processes.

Machine translation

This seminal task, which combines the challenges of natural language understanding, natural language generation and multi-lingual methods, has inspired new approaches like sequence-to-sequence models and attention mechanisms.

Products & Startups

The progress in research and engineering has born a wave of startups competing with the established players. Founders of top startups in the space will share how they are building growing platforms and businesses around speech, translation and conversation.

Track / Schedule

Learning representations with self-attention

With Jakob Uszkoreit

How well can text representations address lexical composition?

With Vered Shwartz

Out-of-distribution detection for neural NLP models

With Hrant Khachatrian

Chargrid: towards understanding 2D documents

With Christian Reisswig

Panel: representations, interpretability & visualisation

With Jakob Uszkoreit, Vered Shwartz, Hrant Khachatrian & Christian Reisswig

Explore: research suggestions at your fingertips

With Richard Zens

Practical transfer learning for NLP with spaCy and Prodigy

With Ines Montani

Coffee break

Large contexts in neural machine translation

With Andrei Popescu-Belis

Interactive and adaptive translation for professionals

With Joern Wuebker

Near real-time multilingual customer service

With João Graça

Panel: machine translation

With Andrei Popescu-Belis, João Graça & Joern Wuebker

Coffee break

Towards breaking the closed-world assumption in deep neural networks

With Michele Sama

Enabling speech-to-meaning with acoustic language processing

With Nicolas Perony

Building a live recommendation agent for communication in healthcare

With Lars Maaløe

Panel: products & startups

With Nicolas Perony, Lars Maaløe, João Graça, Michele Sama, Joern Wuebker & Ines Montani

Track / Speakers

Jakob Uszkoreit

Co-founder, Inceptive

Nicolas Perony

CTO, OTO.ai

Andrei Popescu-Belis

Professor, HEIG-VD

Lars Maaløe

CTO, Corti

Vered Shwartz

PhD Student, Bar-Ilan University

Hrant Khachatrian

Data Scientist, IntelinAir - Researcher, YerevaNN

Christian Reisswig

Senior Data Scientist, SAP SE

João Graça

CTO, Unbabel

Michele Sama

CTO, Kare

Richard Zens

Staff Research Scientist, Google

Joern Wuebker

Director of Research, Lilt

Ines Montani

Founder, Explosion AI

Track / Co-organizers

Adam Bittlingmayer

CEO & Co-founder, ModelFront

AMLD EPFL 2019 / Tracks & talks

AI & Health

Sunil Mallya, Elaine Nsoesie, Asif Jan, Gloria Macia, Evgeniy Gabrilovich, Tomas Dikk, Gabriel Krummenacher, Wojciech Samek, Thomas Hugle, Ali Oskooei, Eirini Arvaniti, Matthias Kämpf, Michael Tangermann, David Hübner, Valeria De Luca

09:00-12:30 January 295ABC

AI & Language

Jakob Uszkoreit, Nicolas Perony, Andrei Popescu-Belis, Lars Maaløe, Vered Shwartz, Hrant Khachatrian, Christian Reisswig, João Graça, Michele Sama, Richard Zens, Joern Wuebker, Ines Montani

13:30-17:00 January 285ABC

AI & Transport

Sunil Mallya, Erik Nygren, Francisco Pereira, Matthieu Cord, Arnaud de La Fortelle, Julian Kooij, Adrien Gaidon, Roxanne Tison, Alberto Chiappa, Mark Meeder, Adrian Egli

09:00-12:30 January 293A

AMLD / Global partners