Videos

See AI2's full collection of videos on our YouTube channel.
Viewing 1-10 of 206 videos
  • Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE Thumbnail

    Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE

    November 18, 2022  |  Yuling Gu
    Figurative language (e.g., "he flew like the wind") is challenging to understand, as it is hard to tell what implicit information is being conveyed from the surface form alone. We hypothesize that to perform this task well, the reader needs to mentally elaborate the scene being described to identify a sensible…
  • Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement Thumbnail

    Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement

    November 16, 2022  |  Bhavana Dalvi Mishra
    EMNLP'22 talk for paper: https://www.semanticscholar.org/paper/Towards-Teachable-Reasoning-Systems%3A-Using-a-Memory-Dalvi-Tafjord/e7d75b80e0fa3ae190ff91676dbf18a006d3a311 Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and…
  • Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning Thumbnail

    Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning

    November 16, 2022  |  Bhavana Dalvi
    EMNLP '22 Talk for paper: https://www.semanticscholar.org/paper/Explaining-Answers-with-Entailment-Trees-Dalvi-Jansen/4a56f72b9c529810ba4ecfe9eac522d87f6db81d Our goal is a question-answering (QA) system that can show how its answers are implied by its own internal beliefs via a systematic chain of reasoning…
  • Biomedical AI for Precision Health Thumbnail

    Biomedical AI for Precision Health

    August 16, 2022  |  Hoifung Poon
    Abstract: The advent of big data promises to revolutionize medicine by making it more personalized and effective, but big data also presents a grand challenge of information overload. For example, tumor sequencing has become routine in cancer treatment, yet interpreting the genomic data requires painstakingly…
  • Beyond End-to-end: Decomposed Modeling and Representations in NLP Thumbnail

    Beyond End-to-end: Decomposed Modeling and Representations in NLP

    July 22, 2022  |  Ido Dagan
    ABSTRACT: Deep learning has pushed us to develop models and representations which we understand and control to a much lesser degree than earlier methods. In this talk I suggest revisiting the pursuit of decomposed models and representations, aiming to regain a better understanding and control of our systems while…
  • "Computers don't have common sense" with Dr. Oren Etzioni Thumbnail

    "Computers don't have common sense" with Dr. Oren Etzioni

    July 13, 2022  |  Oren Etzioni
    Allen Institute for AI or AI2 is the brainchild of the late Paul Allen, philanthropist, and Microsoft co-founder. Dr. Oren has also been a part of the organisation from its inception. Being a renowned expert in the field of AI and a serial entrepreneur, he has helped pioneer meta-search, online comparison…
  • Applied AI in High-Expertise Settings, or Curation as Programming Thumbnail

    Applied AI in High-Expertise Settings, or Curation as Programming

    June 29, 2022  |  Bill Howe
    The success of large AI models in challenging (yet conceptually simple) perception and comprehension tasks (e.g., generating images from a text description) is motivating new applications of these methods in areas previously considered to require human expertise. For example, deep learning has shown promise in…
  • Machines Making Moral Decisions Thumbnail

    Machines Making Moral Decisions

    June 22, 2022  |  Kurt Gray
    Abstract: Humans are increasingly working with AI-powered algorithms, sharing the road with autonomous vehicles, sharing hospital wards with autonomous surgery robots, and making joint decisions with autonomous algorithms. As we adapt to the increasing presence of AIs playing significant roles in our…
  • Time Waits for No One! Analysis and Challenges of Temporal Misalignment Thumbnail

    Time Waits for No One! Analysis and Challenges of Temporal Misalignment

    June 14, 2022  |  Kelvin Luu
    When an NLP model is trained on text data from one time period and tested or deployed on data from another, the resulting temporal misalignment can degrade end-task performance. In this work, we establish a suite of eight diverse tasks across different domains (social media, science papers, news, and reviews) and…
  • Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts Thumbnail

    Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts

    June 10, 2022  |  Daniel Khashabi
    Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the feasibility of extracting a discrete (textual) interpretation of continuous prompts that is faithful to the problem they solve. In…