The Taub Faculty of Computer Science Events and Talks

Deep learning has become pervasive in everyday life, powering language applications like Apple's Siri, Amazon's Alexa, and Google Translate. The inherent limitation of these deep learning systems, however, is that they often function as a ''black box'', preventing researchers and users from discerning the roles of different components and what they learn during the training process. In this talk, I will describe my research on interpreting deep learning models for language along three lines. First, I will present a methodological framework for investigating how these models capture various language properties. The experimental evaluation will reveal a learned hierarchy of internal representations in deep models for machine translation and speech recognition. Second, I will demonstrate that despite their success, deep models of language fail to deal even with simple kinds of noise, of the type that humans are naturally robust to. I will then propose simple methods for improving their robustness to noise. Finally, I will turn to an intriguing problem in language understanding, where dataset biases enable trivial solutions to complex language tasks. I will show how to design models that are more robust to such biases, and learn less biased latent representations. Short Bio: ========== Yonatan Belinkov is a Postdoctoral Fellow at the Harvard School of Engineering and Applied Sciences (SEAS) and the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). His research interests focus on interpreting language representations in neural network models, with applications in machine translation and speech recognition. He received PhD and SM degrees from MIT in 2018 and 2014, and prior to that a BSc in Mathematics and an MA in Arabic Studies, both from Tel Aviv University. He received a Harvard Mind Brain Behavior Postdoctoral Fellowship.