Abstract: In this talk, I will mainly discuss a task-based approach to measure the effect of various pretraining objectives (e.g., language modeling, CCG supertagging) of sentence encoders on their understanding of function words. The tasks[…]
Abstract Spoken communication is basic to who we are. Neurological conditions that result in loss of speech can be devastating for affected patients. This talk will summarize recent efforts in decoding neural activity directly from[…]
Abstract Despite their often-discussed advantages, deep learning methods largely disregard theories of both learning and language. This makes their prediction behavior hard to understand and explain. In this talk, I will present a path toward[…]
Abstract In my talk I will overview five research contributions in the field of neural machine translation recently conducted with my colleagues at Amazon AI and my students at FBK. I will start presenting work on (i)[…]
Abstract In defining “language understanding” for the purposes of natural language processing (NLP), we must inevitably be informed by human cognition: the only existing system that has achieved language understanding. Use of human cognition to[…]
Abstract Data science has begun to have impact in a broad range of disciplines from biomedicine to the humanities. Our view of data science is often highly abstract and mathematical. This view is in contrast to the lived experience of data scientists, who spend much[…]
Title New Twists for New Tricks, Making Audio Deep Learning Practical Abstract Deep Learning has undeniably changed the way we think about audio processing during the last five years. But in the process, it has[…]
