Selected Talks


  • When BERT plays the lottery, all tickets are winning.
    18 Sep 2020: NYU Center for Data Science (online).
  • 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]


  • 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]


  • 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]