Videos

See AI2's full collection of videos on our YouTube channel.
Viewing 21-30 of 177 videos
  • Heroes of NLP: Oren Etzioni Thumbnail

    Heroes of NLP: Oren Etzioni

    October 13, 2020  |  DeepLearning.AI
    Heroes of NLP is a video interview series featuring Andrew Ng, the founder of DeepLearning.AI, in conversation with thought leaders in NLP. Watch Andrew lead an enlightening discourse around how these industry and academic experts started in AI, their previous and current research projects, how their…
  • Is GPT-3 Intelligent? A Directors' Conversation with Oren Etzioni Thumbnail

    Is GPT-3 Intelligent? A Directors' Conversation with Oren Etzioni

    October 1, 2020  |  Stanford HAI
    In this latest Directors’ Conversation, HAI Denning Family Co-director John Etchemendy’s guest is Oren Etzioni, Allen Institute for Artificial Intelligence CEO, company founder, and professor of computer science. Here the two discuss language prediction model GPT-3, a better approach to an AI Turing test, and the…
  • Choosing the Right Statistical Approach to Assess Hypotheses – ACL 2020 Thumbnail

    Choosing the Right Statistical Approach to Assess Hypotheses – ACL 2020

    July 13, 2020  |  Daniel Khashabi
    A survey of hypotheses assessing tools in NLP and their comparison. Further details can be found in the paper 'Not All Claims are Created Equal: Choosing the Right Approach to Assess Your Hypotheses'. https://www.semanticscholar.org/paper/Not-All-Claims-are-Created-Equal%3A-Choosing-the-to-Azer-Khashabi…
  • Syntactic Search by Example – ACL 2020 Thumbnail

    Syntactic Search by Example – ACL 2020

    July 6, 2020  |  Micah Schlain
    Micah Sclain discusses the work on syntactic search happening at AI2 Israel. Check out our system: https://allenai.github.io/spike/
  • Learning and Applications of Paraphrastic Representations for Natural Language Thumbnail

    Learning and Applications of Paraphrastic Representations for Natural Language

    June 18, 2020  |  John Wieting
    Representation learning has had a tremendous impact in machine learning and natural language processing (NLP), especially in recent years. Learned representations provide useful features needed for downstream tasks, allowing models to incorporate knowledge from billions of tokens of text. The result is better…
  • Neuro-symbolic Learning Algorithms for Automated Reasoning Thumbnail

    Neuro-symbolic Learning Algorithms for Automated Reasoning

    April 30, 2020  |  Forough Arabshahi
    Humans possess impressive problem solving and reasoning capabilities, be it mathematical, logical or commonsense reasoning. Computer scientists have long had the dream of building machines with similar reasoning and problem solving abilities as humans. Currently, there are three main challenges in realizing this…
  • From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project Thumbnail

    From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project

    March 27, 2020  |  Peter Clark
    AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even as recently as 2016, the best AI system could achieve merely 59.3% on an 8th Grade science exam. This talk reports success on the…
  • Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Thumbnail

    Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

    January 6, 2020  |  Colin Raffel
    Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this…
  • Towards AI Complete Question Answering: Combining Text-based, Unanswerable and World Knowledge Questions Thumbnail

    Towards AI Complete Question Answering: Combining Text-based, Unanswerable and World Knowledge Questions

    December 11, 2019  |  Anna Rogers
    The recent explosion in question answering research produced a wealth of both reading comprehension and commonsense reasoning datasets. Combining them presents a different kind of challenge: deciding not simply whether information is present in the text, but also whether a confident guess could be made for the…
  • Learning Dynamics of LSTM Language Models Thumbnail

    Learning Dynamics of LSTM Language Models

    November 20, 2019  |  Naomi Saphra
    Research has shown that neural models implicitly encode linguistic features, but there has been little work exploring how these encodings arise as the models are trained. I will be presenting work on the learning dynamics of neural language models from a variety of angles. Using Singular Vector Canonical…