Videos

See AI2's full collection of videos on our YouTube channel.
All Years
All Videos
Viewing 41-50 of 171 videos
  • Understanding Time In Natural Language Thumbnail

    Understanding Time In Natural Language

    January 25, 2019  |  Qiang Ning
    Time is an important dimension when we describe the world because the world is evolving over time and many facts are time-sensitive. Understanding time is thus an important aspect of natural language understanding and many applications may rely on it, e.g., information retrieval, summarization, causality, and… more
  • Text Generation from Knowledge Graphs Thumbnail

    Text Generation from Knowledge Graphs

    January 11, 2019  |  Rik Koncel-Kedziorski
    In this talk I will introduce a new model for encoding knowledge graphs and generating texts from them. Graphical knowledge representations are ubiquitous in computing, but pose a challenge for text generation techniques due to their non-hierarchical structure and collapsing of long-distance dependencies… more
  • Using cognitive science to evaluate and interpret neural language models Thumbnail

    Using cognitive science to evaluate and interpret neural language models

    December 14, 2018  |  Tal Linzen
    Recent technological advances have made it possible to train recurrent neural networks (RNNs) on a much larger scale than before. While these networks have proved effective in NLP applications, their limitations and the mechanisms by which they accomplish their goals are poorly understood. In this talk, I will… more
  • Natural Language Interface for Web Interaction via Compositional Generation Thumbnail

    Natural Language Interface for Web Interaction via Compositional Generation

    December 12, 2018  |  Panupong (Ice) Pasupat
    Natural language understanding models have achieved good enough performance for commercial products such as virtual assistants. However, their scopes are mostly still limited to preselected domains or simpler sentences. I will present my line of work which extends natural language understanding in two frontiers… more
  • Towards Agents that can See, Talk, and Act Thumbnail

    Towards Agents that can See, Talk, and Act

    December 11, 2018  |  Abhisek Das
    Building intelligent agents that possess the ability to perceive the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and execute actions in a physical environment, is a long-term goal of Artificial Intelligence. In this talk, I will present some of… more
  • Learning Common Sense: A Grand Challenge for Academic AI Research Thumbnail

    Learning Common Sense: A Grand Challenge for Academic AI Research

    December 6, 2018  |  Oren Etzioni
    Dr. Oren Etzioni, Chief Executive Officer of the Allen Institute for AI and professor of computer science at the University of Washington, addresses one of the Holy Grails of AI: acquiring, representing and utilizing common-sense knowledge, during a distinguished lecture series held at the Office of Naval… more
  • Learning with Less Supervision in a Multilingual World Thumbnail

    Learning with Less Supervision in a Multilingual World

    November 16, 2018  |  Shyam Upadhyay
    Lack of annotated data is a constant obstacle in developing machine learning models, especially for natural language processing (NLP) tasks. In this talk, I explore this problem in the realm of Multilingual NLP, where the challenges become more acute as most of the annotation efforts in the NLP community have… more
  • Efficient Algorithms for Adaptive Data Collection with Very Large Action Spaces Thumbnail

    Efficient Algorithms for Adaptive Data Collection with Very Large Action Spaces

    November 12, 2018  |  Kevin Jamieson
    In many science and industry applications, data-driven discovery is limited by the rate of data collection like the time it takes skilled labor to operate a pipette or the cost of expensive reagents or use of experimental apparatuses. When measurement budgets are necessarily small, adaptive data collection that… more
  • Rational Recurrences: Bridging CNNs, RNNs, and Weighted Finite-State Machines Thumbnail

    Rational Recurrences: Bridging CNNs, RNNs, and Weighted Finite-State Machines

    October 26, 2018  |  Sam Thomson
    Is there a class of models that perform competitively with LSTMs, yet are interpretable, parallelizable, data-efficient, and whose mathematical properties are already well-studied? I will present a recent line of work where we show that weighted finite-state automata (WFSAs) can be made unreasonably effective… more
  • Building Unsupervised Versatile Agents with Meta-Learning Thumbnail

    Building Unsupervised Versatile Agents with Meta-Learning

    October 22, 2018  |  Chelsea Finn
    Machine learning excels primarily in settings where an engineer can first reduce the problem to a particular function, and collect a substantial amount of labeled input-output pairs for that function. In drastic contrast, humans are capable of learning a range of versatile behaviors from streams of raw sensory… more