时间：2016年1月15日 下午 2:00
The goal of deep learning for natural language processing (DL4NLP) at Noah’s Ark Lab is to build neural network systems that can communicate with humans and help them on real-world tasks, particularly machine translation and natural language dialogue. To this end, we need to make breakthrough on various aspects of natural language processing, including analysis, representation, and generation of language, as well as acquisition and utilization of knowledge, inference, and planning. This calls for not only new data structures and new architectures, but also new learning mechanisms to accomplish the tasks with previously unseen complexity and scale.
In this talk, I will give an overview of research on DL4NLP conducted at the lab. I will first summarize the major achievements made by the lab, including development of models for sentence representation, semantic matching, image retrieval, machine translation, and natural language dialogue. I will then explain in details about our recent work, including a neural network for machine translation called DeepMemory, a neural network l for generative question answering called GenQA, and a neural network for reasoning over natural language sentences called Neural Reasoner. I will conclude the talk by showing our vision on DL4NLP.
Hang Li is director of the Noah’s Ark Lab of Huawei Technologies, adjunct professors of Peking University and Nanjing University. His research areas include information retrieval, natural language processing, statistical machine learning, and data mining. He graduated from Kyoto University in 1988 and earned his PhD from the University of Tokyo in 1998. He worked at the NEC lab as researcher during 1991 and 2001, and Microsoft Research Asia as senior researcher and research manager during 2001 and 2012. He joined Huawei Technologies in 2012. Hang has published three technical books, and more than 100 technical papers at top international conferences including SIGIR, WWW, WSDM, ACL, EMNLP, ICML, NIPS, SIGKDD and top international journals including CL, NLE, JMLR, TOIS, IRJ, IPM, TKDE, TWEB, TIST. He and his colleagues’ papers received the SIGKDD’08 best application paper award, the SIGIR’08 best student paper award, the ACL’12 best student paper award. Hang worked on the development of several products such as Microsoft SQL Server 2005, Office 2007, Office 2010, Live Search 2008, Bing 2009, Bing 2010. He has 40 granted US patents. Hang is also very active in the research communities and has served or is serving top international conferences as PC chair, Senior PC member, or PC member, including SIGIR, WWW, WSDM, ACL, EMNLP, NIPS, SIGKDD, ICDM, ACML, and top international journals as associate editor or editorial board member, including CL, IRJ, TIST, JASIST, JCST. He is ACM Distinguished Scientist.