报告时间：1月9日上午10:00 – 11:00
报告地点：浙江大学紫金港校区蒙民伟楼402室
报告人：Dr. Zhouhan Lin
主持人：蔡登教授
Title: Learning Structured Representations for Natural Language

Abstract: In this talk, we’ll cover several approaches in learning structured representations for natural language, which could benefit applications in various downstream tasks. We’ll start from introducing a self-attentive sentence embedding, which aims at learning intra-sentence relation through attention mechanism and represent the semantics of a sentence in a matrix representation. Then I’ll describe two models with the capability to learn richer structures in two different ways: a discretized way through reinforcement learning, and a softened way through backpropagation. The discretized way is an adaptive neural network that reflects the language structure directly through the structure of the neural networks; while the softened way is a language model capable of learning implicit structures in the form of a binary tree. Finally, I’ll show a sample application of the second application to a classical NLP task, which is syntactic parsing.

Bio: Zhouhan is a 5-th year Ph.D. student at MILA, University of Montreal, under the supervision of Yoshua Bengio. He received his BS and MS degree in Harbin Institute of Technology. His areas of expertise include machine learning and natural language processing, especially in attention mechanisms and its applications, language modeling, question answering, syntactic parsing, and binary networks. He has published 6 top conference papers and 10+ other papers in other venues such as workshops and journals. His full publication list could be found at https://scholar.google.ca/citations?user=LNZ4efwAAAAJ&hl=en.