Abstract Adversarial machine learning research has been nearly obsessed with test-time attacks on image (and to a lesser degree, text) classification tasks.  This talk examines two directions that broaden the anticipated threats.  First, I discuss[…]

Read More

Abstract In this three part talk, I will present some of our recent efforts that aim to control and adapt neural models to work more effectively in end applications. The first part will focus on[…]

Read More

Title: Recognizing Sound Events Abstract: The Sound Understanding team at Google has been developing automatic sound classification tools with the ambition to cover all possible sounds – speech, music, and environmental. I will describe our application[…]

Read More

Cross-Lingual Transfer of Natural Language Processing Systems Accurate natural language processing systems rely heavily on annotated datasets. In the absence of such datasets, transfer methods can help to develop a model by transferring annotations from[…]

Read More

Abstract We tackle the challenge of understanding voice queries posed against the Comcast Xfinity X1 entertainment platform, where consumers direct speech input at their “voice remotes”. Such queries range from specific program navigation (i.e., watch[…]

Read More

Abstract How universal is human conceptual structure? The way concepts are organized in the human brain may reflect distinct features of cultural, historical, and environmental background in addition to properties universal to human cognition. Semantics,[…]

Read More

Abstract The Marian toolkit dominated a shared task on translation speed run by the Workshop on Neural Machine translation. Speed came from many levels: model complexity, teacher-student compression, and efficient kernels.  Compressing the model is[…]

Read More