Avatar

Benjamin Muller

PhD student in Natural Language Processing

INRIA

Sorbonne Université

I am a third-year PhD student at Sorbonne Université and INRIA Paris in the Almanach research team. My research focuses on understanding the behavior of large scale language models and applying them efficiently in the multilingual context. I have interned at Apple AI/ML and Amazon Alexa AI. I am also the main instructor for the Machine Learning for NLP course at ENSAE Paris.

Interests

  • Natural Language Processing
  • Deep Learning

Education

  • PhD in Machine Learning applied to Natural Language Processing, 2022

    INRIA & Sorbonne Université

  • MSc Data Science, 2016

    Ecole Polytechnique, ENSAE, Télécom Paris

  • BSc in Statistics, 2014

    ENSAE

Publications

Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, Alessandro Moschitti (2021). Cross-Lingual GENQA: A Language-Agnostic Generative Question Answering Approach for Open-Domain Question Answering. arxiv.

PDF

Benjamin Muller, Antonios Anastasopoulos, Benoît Sagot, Djamé Seddah (2021). When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models. NAACL.

PDF

Benjamin Muller, Yanai Elazar, Benoit Sagot, Djamé Seddah (2021). First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT. EACL.

PDF

Louis Martin*, Benjamin Muller*, Pedro Javier Ortiz Suárez*, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah, Benoît Sagot (2020). CamemBERT: a Tasty French Language Model. ACL.

PDF Project

Benjamin Muller, Benoit Sagot, Djamé Seddah (2019). Enhancing BERT for Lexical Normalization. WNUT.

PDF

See all publications

Talks

JHU CSLP Seminar, Cross-Lingual Transfer with Multilingual Language Models

Benjamin Muller
Mar 31, 2022

George Mason Natural Language Processing Group , Virginia, Toward a Cross-Lingual Generative Question Answering System

Benjamin Muller
Dec 2, 2021

ITU Copenhagen, When Being unseen by mBERT is just the beginning, Handling New Languages With Multilingual Language Models

Benjamin Muller
Jan 15, 2021

EDF Data Innovation Lab, Paris, CamemBERT: a Tasty French Language Model

Benjamin Muller
Sep 8, 2020

Bar Ilan University, Tel-Aviv, Transfer Learning on an Unseen North-African Arabic Dialect, December 2019

Benjamin Muller
Nov 30, 2019

Teaching

2019-2022 - Lecturer and Main Instructor at ENSAE Paris for the Machine Learning for Natural Language Processing course.

2018-2019 - Teaching assistant for Master students in Initiation to Research in Statistics at University Paris-Descartes

2014-2016 - Teaching assistant for Bachelor students in Mathematics, Prépa ECS at Lycée Ipécom, Paris

Mentoring

2022 - Mentor for the Fatima Fellowship program. Mentoring 3 students in analysing cultural biases in multilingual language models.

2018-2022 - Supervising MSc students’ research projects. Focusing on implementation, evaluation and analysis of static Word Embedding techniques and Language Modeling.

2019 - Supervising internship on Domain Adaptation for Non-Canonical Data (6 months)