题目：Combining CNN and RNN for Text Classification

内容简介：Neural networks have been demonstrated to be capable of achieving remarkable performance in sentence and document modeling. Convolutional neural network(CNN) and recurrent neural network (RNN) are two mainstream architectures for such modeling tasks, which adopt totally different ways of understanding natural languages. In this work, we combine the strengths of both architectures and propose a novel and unified model  called C-LSTM for  sentence representation and text classification. C-LSTM utilizes CNN to  extract a sequence of higher-level phrase representations, which  are fed into  a long short-term memory recurrent neural network (LSTM) to obtain the sentence representation. C-LSTM is  able to capture both local features of phrases as well as  global and temporal sentence semantics. We evaluate the proposed architecture on sentiment classification and question classification tasks. The experimental results show that the C-LSTM outperforms both CNN and LSTM and can achieve excellent performance on these tasks. This is joint work with Chunting Zhou, Chonglin Sun, and Zhiyuan Liu.

报告人：香港大学刘智满教授

报告人简介：Francis Chi Moon Lau received his Bsc in computer science from Acadia University, and MMath and PhD in computer science from University of Waterloo. He joined the department of Computer Science at the University of Hong Kong in 1987. He is currently Professor in Computer Science and Associate Dean of Engineering at HKU. His research interests include systems (both practical and theoretical), and the application of computing to arts, in particular music. Prof. Lau serves on a number of editorial boards, including the editor-in-chief for the Journal of Interconnection Networks. He has published over 300 papers in prestigious journals and conferences, and won several best papers awards including APSys 2016, HotPOST 2012, ICEC 2010 and I-SPAN 2008.

时间：2018年5月7日（周一）上午10：00始

地点：南海楼224室

热烈欢迎广大师生参加!

信息科学技术学院/网络空间安全学院

2018年5月7日