清華大學資工系

Department of Computer Science

專題演講SEMINA

主講人(SPEAKER)：馬維英博士，謝幸博士，劉鐵岩博士, Microsoft Research Asia(馬維英博士為清華校友)

 題目(TOPIC)：

 Towards Machine Comprehension of Text  (Wei-Ying Ma)

User Understanding from Large Scale Human Behavioral Data (Xing Xie)

Computational Advertising:  Challenges and Opportunities (Tie-Yan Liu)

時間(DATE)：103 年11月 20日 (四) 14:00-15:30

地點(PLACE)：台達館109室

                                                                                                                                                                                                                                                                                                                                                                                                                                                               聯絡人：張俊盛教授

Towards Machine Comprehension of Text

Speaker: Wei-Ying Ma, Microsoft Research Asia

Abstract:

In recent years, we have seen dramatic improvements in deep learning, knowledge (entity) mining, and computing infrastructure that are providing powerful capabilities to process and understand text data at an unprecedented scale. We now have the ability to learn big statistical models from large amounts of data and build comprehensive symbolic knowledge graphs from the Web. We have technologies to learn different types of representations for text, including continuous vector space models based on semantic embedding, graph representations based on entity and relationship extraction, and discrete representations using information retrieval based approaches. We have distributed graph engines capable of serving a large-scale knowledge graph on which natural language understanding and generation can be performed in real time. In the industry, the rise of intelligent software such as Microsoft Cortana gives us opportunities to close the human feedback loop and create never-ending knowledge mining and machine learning to monotonically improve the precision and coverage of the various text representations. By building a scalable system and algorithms to leverage and integrate all these capabilities, we could unify many fundamental building blocks in natural language understanding, such as semantic parsing and linking of text string onto knowledge graph and reasoning and inference with common sense to decipher its meaning. In this talk, I will introduce some of our work in this area, including knowledge powered word embedding, automatic construction of a knowledge graph, and real time graph search and knowledge-based question answering.

Dr. Wei-Ying Ma is an Assistant Managing Director at Microsoft Research Asia, where he oversees multiple research groups, including Web Search and Data Management, Natural Language Computing, Knowledge Mining, Machine Learning, and Internet Economics and Computational Advertising. He and his team of researchers have developed many key technologies that have been transferred to Microsoft’s Applications and Services Group, including Bing Search Engine and Microsoft Advertising. He has published more than 250 papers at international conferences and in journals. He is a Fellow of the IEEE and a Distinguished Scientist of the ACM. He served on the editorial boards of ACM Transactions on Information System (TOIS) and is a member of the International World Wide Web (WWW) Conferences Steering Committee. In recent years, he has served as program co-chair of WWW 2008 and as general co-chair of ACM SIGIR 2011. More information about him can be found at http://research.microsoft.com/en-us/people/wyma/

User Understanding from Large Scale Human Behavioral Data

Speaker: Xing Xie, Senior Researcher, Microsoft Research Asia

Abstract:

With the rapid development of positioning, sensor and smart device technologies, large quantities of human behavioral data are now readily available. They reflect various aspects of human mobility and activities in the physical world. The availability of this data presents an unprecedented opportunity to gain a more in depth understanding of users and provide them with personalized online experience while respecting their privacy. In this talk, I will present a number of our recent research efforts on this direction, including user mobility understanding and prediction, user linking across multiple networks, psychological trait inference, and life pattern analysis.

Dr. Xing Xie is currently a senior researcher in Microsoft Research Asia, and a guest Ph.D. advisor for the University of Science and Technology of China. He received his B.S. and Ph.D. degrees in Computer Science from the University of Science and Technology of China in 1996 and 2001, respectively. He joined Microsoft Research Asia in July 2001, working on spatial data mining, location based services, social networks and ubiquitous computing. During the past years, he has published over 140 referred journal and conference papers. He has more than 50 patents filed or granted. He currently serves on the editorial boards of ACM Transactions on Intelligent Systems and Technology (TIST), Springer GeoInformatica, Elsevier Pervasive and Mobile Computing, Journal of Location Based Services, and Communications of the China Computer Federation (CCCF). He has worked as a guest editor of IEEE Transactions on Multimedia and IEEE Intelligent Systems. In recent years, he was involved in the program or organizing committees of over 70 conferences and workshops. Especially, he initiated the LBSN workshop series and served as program co-chair of ACM UbiComp 2011 and program chair of the 8th Chinese Pervasive Computing Conference (PCC 2012). In Oct. 2009, he founded the SIGSPATIAL China chapter which was the first regional chapter of ACM SIGSPATIAL. He is a member of Joint Steering Committee of the UbiComp and Pervasive Conference Series. He is a senior member of ACM, the IEEE, and China Computer Federation (CCF).

Computational Advertising:  Challenges and Opportunities

Speaker: Tie-Yan Liu, Senior Researcher, Microsoft Research Asia

Abstract:

Computational advertising has become a hot research direction these years, mainly due to the huge success of the business model of online advertising. It is a cross discipline, and has strong connections with information retrieval, machines learning, algorithmic game theory, and micro-economics. In this talk, I will make some basic introduction to computational advertising, and discuss a few fundamental research problems regarding computational advertising. This includes user click behavior modeling, advertiser bidding behavior modeling, and optimal auction mechanism design. I will then introduce our recent works along these directions, including psychological click model, Markov bidding behavior model, and game-theoretical learning for auction optimization.

Dr. Tie-Yan Liu is a senior researcher and research manager at Microsoft Research Asia. His research interests include machine learning, information retrieval, data mining, computational advertising, and algorithmic game theory. He is well known for his pioneer work on learning to rank for information retrieval. He has authored the first book in this area, and published tens of impactful papers on both algorithms and theorems of learning to rank. In addition, his paper on graph mining won the best student paper award of SIGIR (2008); his paper on video shot boundary detection won the most cited paper award of the Journal of Visual Communication and Image Representation (2004-2006); and his work on Internet economics won the research break-through award of Microsoft Research Asia (2012). Tie-Yan is very active in serving the research community. He is a program committee co-chair of ACML (2015), WINE (2014), AIRS (2013), and RIAO (2010), a local co-chair of ICML 2014, a tutorial co-chair of SIGIR (2016) and WWW (2014), a doctorial consortium co-chair of WSDM (2015), a demo/exhibit co-chair of KDD (2012), and an area/track chair or senior program committee member of many conferences including KDD (2015), ACML (2014), SIGIR (2008-2011), AIRS (2009-2011), and WWW (2011, 2015). He is an associate editor of ACM Transactions on Information System (TOIS), an editorial board member of Information Retrieval Journal (IRJ) and Foundations and Trends in Information Retrieval (FnTIR). He is a keynote speaker at ECML/PKDD (2014), CCIR (2011, 2014), CCML (2013), and PCM (2010), a tutorial speaker at SIGIR (2008, 2010, 2012), WWW (2008, 2009, 2011), and KDD (2012), and a plenary panelist at KDD (2011). He is a senior member of the IEEE and the ACM, as well as a senior member and distinguished speaker of the CCF. He is currently an adjunct professor of Carnegie Mellon University (LTI), Nankai University, Sun Yat-Sen University, and University of Science and Technology of China; and an Honorary Professor of University of Nottingham.