Videos

See AI2's full collection of videos on our YouTube channel.
Viewing 141-150 of 249 videos
  • Acquiring Lexical Semantic Knowledge Thumbnail

    Acquiring Lexical Semantic Knowledge

    June 7, 2018  |  Vered Shwartz
    Recognizing lexical inferences is one of the building blocks of natural language understanding. Lexical inference corresponds to a semantic relation that holds between two lexical items (words and multi-word expressions), when the meaning of one can be inferred from the other. In reading comprehension, for…
  • Found in Translation: the journey to achieving human parity in Machine Translation Thumbnail

    Found in Translation: the journey to achieving human parity in Machine Translation

    May 18, 2018  |  Hany Hassan
    Machine translation has made rapid advances in recent years. Millions of people are using it today in online translation systems and mobile applications in order to communicate across language barriers. The question naturally arises whether such systems can approach or achieve parity with human translations. In…
  • Deep Representation Learning with Induced Structural Priors Thumbnail

    Deep Representation Learning with Induced Structural Priors

    May 8, 2018  |  Saining Xie
    With the support of big-data and big-compute, deep learning has reshaped the landscape of research and applications in artificial intelligence. Whilst traditional hand-guided feature engineering in many cases is simplified, the deep network architectures become increasingly more complex. A central question is if…
  • New Resources and Ideas for Semantic Parsing Thumbnail

    New Resources and Ideas for Semantic Parsing

    April 20, 2018  |  Kyle Richardson
    In this talk, I will give an overview of research being done at the University of Stuttgart on semantic parser induction and natural language understanding. The main topic, semantic parser induction, relates to the problem of learning to map input text to full meaning representations from parallel datasets. Such…
  • Open Loop Hyperparameter Optimization and Determinantal Point Processes Thumbnail

    Open Loop Hyperparameter Optimization and Determinantal Point Processes

    April 10, 2018  |  Jesse Dodge
    Driven by the need for parallelizable hyperparameter optimization methods, we study open loop search methods: sequences that are predetermined and can be generated before a single configuration is evaluated. Examples include grid search, uniform random search, low discrepancy sequences, and other sampling…
  • Connecting Vision and Language for Interpretation, Grounding and Imagination Thumbnail

    Connecting Vision and Language for Interpretation, Grounding and Imagination

    April 2, 2018  |  Rama Vedantam
    Understanding how to model vision and language jointly is a long-standing challenge in artificial intelligence. Vision is one of the primary sensors we use to perceive the world, while language is our data structure to represent and communicate knowledge. In this talk, we will take up three lines of attack to…
  • Robust Text Correction for Grammar and Fluency Thumbnail

    Robust Text Correction for Grammar and Fluency

    March 30, 2018  |  Keisuke Sakaguchi
    Robustness has always been a desirable property for natural language processing. In many cases, NLP models (e.g., parsing) and downstream applications (e.g., MT) perform poorly when the input contains noise such as spelling errors, grammatical errors, and disfluency. In this talk, I will present three recent…
  • Debiasing natural language evaluation with humans in the loop Thumbnail

    Debiasing natural language evaluation with humans in the loop

    March 28, 2018  |  Arun Chaganty
    A significant challenge in developing systems for tasks such as knowledge base population, text summarization or question answering is simply evaluating their performance: existing fully-automatic evaluation techniques rely on an incomplete set of “gold” annotations that can not adequately cover the range of…
  • Text Representation, Retrieval, and Understanding with Knowledge Graphs Thumbnail

    Text Representation, Retrieval, and Understanding with Knowledge Graphs

    March 26, 2018  |  Chenyan Xiong
    Search engines and other information systems have started to evolve from retrieving documents to providing more intelligent information access. However, the evolution is still in its infancy due to computers’ limited ability in representing and understanding human language. This talk will present my work…
  • Internal Representations in Deep Learning for Language and Speech Processing Thumbnail

    Internal Representations in Deep Learning for Language and Speech Processing

    March 7, 2018  |  Yonatan Belinkov
    Language technology has become pervasive in everyday life, powering applications like Apple’s Siri or Google’s Assistant. Neural networks are a key component in these systems thanks to their ability to model large amounts of data. Contrary to traditional systems, models based on deep neural networks (a.k.a. deep…