Selected Talks

2022

2021

  • BERTology nuggets
    15 December 2021: invited talk at London Machine Learning Meetup, [SLIDES]
  • The Peer Review Process and Widening NLP
    11 November 2021: Panel with Bahar Mehmani and Cecilia Superchi at Widening NLP (co-located with EMNLP 2021)
  • Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics
    10 November 2021: presentation at Workshop on Insights from Negative Results co-located with EMNLP 2021
  • Just what do you think you’re doing, Dave?
    10 November 2021: presentation at NLLP workshop co-located with EMNLP 2021
  • Changing the world by changing the data
    09 November 2021: invited talk at Data-centric AI Day (France is AI) [SLIDES]
  • What we know about how BERT works
  • 27 October 2021: invited talk at Technical University of Denmark, [SLIDES]
  • Panel Discussion on Trustworthy NLP (Google)
    13 October 2021: Panel with Kellie Webster and Hannach Wallach at Google’s Trustworthy NLP Workshop
  • Changing the world by changing the data
    21 September 2021: invited talk at Machine Learning for NLP (Toronto ML Series) [SLIDES]
  • Changing the world by changing the data
    3 August 2021: oral talk at ACL 2021 [SLIDES]
  • Reviewing Natural Language Processing research.
    29 June 2021: tutorial at TALN 2021 (with Kevin Cohen, Karën Fort, Margot Mieskes and Aurélie Névéol)
  • A primer in BERTology: what we know about how BERT works
    June 17 2021: invited talk at L3-AI [SLIDES]
  • A primer in BERTology: what we know about how BERT works
    June 8 2021: presentation at NAACL 2021 [SLIDES]
  • The quest for difficult benchmarks in question answering and reading comprehension.
    7 May 2021: invited talk at LTI Colloquium at Carnegie Mellon University [URL] [SLIDES]
  • Reviewing Natural Language Processing research.
    20 April 2021: tutorial at EACL 2021 (with Kevin Cohen, Karën Fort, Margot Mieskes and Aurélie Névéol)

2020

  • A guide to the dataset explosion in QA, NLI, and commonsense reasoning.
    13 Dec 2020: Tutorial at COLING 2020 (online). [URL] [SLIDES]
  • When BERT plays the lottery, all tickets are winning.
    20 Nov 2020: invited talk at BlackBox NLP (online). [URL]
  • How Much Should Conversational AI Developers know about ML and Linguistics?
    16 Jun 2020: The Level 3 AI Assistant Conference, panel discussion with Emily M. Bender, Thomas Wolf, and Vladimir Vlasov (online). [URL]
  • The questions that the current AI can’t answer
    8 Feb 2020: Evaluating Evaluation of AI Systems (Workshop co-located with AAAI 2020, New York, USA). [SLIDES]

2019

  • Towards AI Complete Question Answering: Combining Text-based, Unanswerable and World Knowledge Questions
    11 December 2019: Allen Institute for Aritficial Intelligence (Seattle, USA).
  • Text Representations Learning and Compositional Semantic (ACML 2019 tutorial)
    November 17 2019: Nagoya, Japan [URL]
  • The dark secrets of BERT
    11 November 2019: RIKEN Center for Computational Science (Tokyo, Japan).
  • Word embeddings: 6 years later
    22 May 2019: UMass Amherst (USA). [SLIDES]

2018

  • What’s in your embedding, and how it predicts task performance.
    27 September 2018: UMass Amherst (USA). [SLIDES], [VIDEO].
    A version of this talk was also presented on August 30 2018 at IT University of Copenhagen (Denmark).
  • Distributional compositional semantics in the age of word embeddings.
    7 May 2018: Tutorial at LREC 2018, Miyazaki, Japan. [URL]
  • Detecting linguistic relations with analogies: what works and what doesn’t.
    July 15 2016: Google Tokyo seminar, Tokyo, Japan. [SLIDES]