Yang Song
 

 

About Me

I have recently join the Machine Intelligence group in Google Research to work on the most cutting-edge problems in deep learning. Specifically, we are building the world's best dialogue engines for Google products using deep learning, NLP and recommender systems. Before that, I was a Senior Software Engineer at Google Seattle working on user modeling and machine learning for Ads.

I spent over 7 years at Microsoft Research before joining Google. I was a Researcher at the Deep Learning Technology Center at Microsoft Research Redmond. Before that, I was a Researcher affiliated with Internet Services Research Center (ISRC)Search Quality & Cyber-Intelligene Lab (SQ-CIL) in MSR Redmond. I joined MSR in 2009 after I got my Ph.D. During my Ph.D, I worked with my advisor C. Lee Giles on the next generation scientific literature search engine CiteSeer.

Here is the link to my Google Scholar page and Google Research page.

We have recently open-sourced our code that implemented Multi-view DNN and Temporal DSSM in Keras [github link].

Education

Ph.D. (2004- 2008) in Computer Science and EngineeringThe Pennsylvania State University
B.S. (1999-2003) in Computer Science and Technology, Zhejiang University, China

Research Interests

My research includes a broad interests of machine learning-related fields, e.g., text classification, information retrieval, search engine ranking, recommender systems and so on.

Deep Learning: Recently, I have been focusing on using deep learning for recommendation, ranking and personalization.

Online User Behavioral Genome Sequencing: my recent research has focused on user behavioral analysis on search engines, mobile devices and other online services in order to create high quality user profiles and better tailor online services to meet the user needs. Our recent WWW 2015 DNN paper and  WWW2014 Demo reveals the tip of the iceberg from this project.

From search session to user tasks: In the past three years, I have been leading a project named Search TrailBlazer that aims at redefining search sessions with tasks. Check out our latest project status and code for scientific uses.

Social tagging Recommendation: I've put up a page regarding my research on recommender systems for social bookmarking.

I've been lucky to have worked with many smart students in the for the summer internships at MSR.

 

Invited Talks

Journal Publications

Referred Conference Proceedings

(*) are students I mentored for their summer internships at MSR.

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

Contact Me:

EMail: ys at sonyis dot me
Microsoft Research
One Microsoft Way
Redmond, WA 98052