Hacking Book | Free Online Hacking Learning

 Home

professor of harbin university of technology: che wanxiang -- deep learning and lexical, syntactic and semantic analysis

Posted by patinella at 2020-02-27
all

Dr. Che Wanxiang, Professor of computer school of Harbin University of technology, doctoral supervisor, visiting scholar of Stanford University, and Professor Christopher Manning, CO supervisor. At present, he is a member of the professional committee of computational linguistics and deputy director of the youth working committee of the Chinese information society; he is a senior member of the Chinese computer society, and once served as the chairman of YOCSEF Harbin (2016-2017). More than 50 academic papers have been published in ACL, emnlp, AAAI, IJCAI and other domestic and foreign high-level journals and conferences, among which AAAI's articles in 2013 have won the outstanding paper honorable quantity award, published 2 textbooks and 2 translations. At present, it has undertaken many scientific research projects such as NSFC and 973. The language technology platform (LTP), which is responsible for research and development, has been shared by more than 600 units, and the online "language cloud" service provided has more than 10000 users, and is authorized to be used by Baidu, Tencent, Huawei and other companies. In 2009, it won the first prize in the international multilingual syntactic and semantic analysis evaluation of connl. In 2015-16, he won Google focused research for two consecutive years Award (Google focused research award); in 2016, won the first prize of Heilongjiang Province Science and technology progress (ranking second); in 2012, won the second prize of Heilongjiang Province Technology Invention Award (ranking second); in 2010, won the first prize of "Qian Weichang" Chinese information processing science and Technology Award (ranking second), the first Hanwang Youth Innovation Award (individual) and many other awards. In 2017, the course "Python language programming" was awarded the national excellent online open course.

Report summary:

Lexical, syntactic and semantic analysis are the basic research tasks of natural language processing. These tasks can be abstracted into structural prediction problems. Different from the classification problem, many output categories in structural prediction are interrelated, and such tasks are often unique to natural language processing. How to use deep learning technology for structural learning is one of the hot issues in the field of natural language processing. This workshop will take lexical analysis (segmentation, part of speech tagging), syntactic analysis (dependency syntactic analysis, phrase structure syntactic analysis) and semantic analysis (semantic role tagging, semantic dependency analysis) as examples to introduce the latest research progress in structure prediction based on deep learning. First of all, it introduces the basic method of using greedy search to predict the structure; then, it introduces the global search method based on dynamic programming, which uses the deep learning method to learn the representation of features as the former method; finally, it introduces how to use the global search method in the learning process to further improve the accuracy of the system.

Report download address: http://cips-

upload.bj.bcebos.com/ssatt2018%2FATT8_3_%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E4%B8%8E%E8%AF%8D%E6%B3%95%E3%80%81%E5%8F%A5%E6%B3%95%E3%80%81%E8%AF%AD%E4%B9%89%E5%88%86%E6%9E%90.pdf

Previous highlights (click to view):

John Edward Hopcroft, academician of the American Academy of Sciences and Turing Award winner: deep learning

Professor of Nanjing University: Zhou Zhihua -- deep forest: exploring methods beyond deep neural network

Li Feifei, director of Artificial Intelligence Laboratory of Stanford University

Professor of Naval Engineering University: Ben Kerong: artificial intelligence technology and its application progress

Tsinghua University: Liu Yang -- machine translation based on deep learning

Professor of National University of Defense Technology: Yin Jianping: the past, present and future of computer science theory

Liu Yunhao, Dean of the school of software, Tsinghua University

Masashi Sugiyama, director of advanced intelligence research center of Japan Institute of science and chemistry

"Character feature" Deng Zhidong, Tsinghua University: "feature extraction + reasoning" small data learning is the key to the rise of AI

Minglue lecture hall Professor Ma Shaoping of Tsinghua University explained in detail "what can artificial intelligence do?"

[original] | Xi'an University of Electronic Science and technology -- Jiao Licheng: the challenge and thinking of deep learning in the era of artificial intelligence

Michael I. Jordan: Computational Thinking, inferential thinking and data science

[original] Wang Feiyue: opportunities and challenges of generative network confrontation

[original] | Microsoft Asia Research Institute Liu Tieyan: Advanced Learning frontier

Professor of Tsinghua University: Sun Fuchun: artificial intelligence and robot in the cognitive age

When Bayes meets big data

University of California, Berkeley: Ma Yi: low dimensional structure and high dimensional model (visual) data

Professor, computer department, University of California, Berkeley: Dawn song -- how AI can build a stronger defense system

Tsinghua University: Liu Zhiyuan -- knowledge representation learning and its application

Li Feifei and the power of Imagenet

Professor of Tsinghua University: Sun Fuchun -- Prospect of core technology of educational robot

From the perspective of high-end talent allocation, the results of the fourth round of the first level discipline evaluation of computer science and technology

Huang Tiejun, Changjiang Scholar and professor of Peking University: the past, present and future of artificial intelligence

© 2023