|
Tom's Web Page |
|
 CSE Home |
About Us |
Search |
Contact Info |
I am a Principal Applied Scientist Manager at Microsoft, where I enable computers to understand natural language text from millions of users.
Recently, I've led the creation and development of
Natural Language understanding for Windows
(Engadget,
PC World,
CNN),
intent understanding for Page Zero
(Engadget,
Neowin),
and also systems for entity extraction.
I have a Ph.D. from UW Computer Science, where I studied NLP and AI and was advised by Professor Oren Etzioni and Professor Mausam.
Professor Etzioni's group developed Open Information Extraction to read and extract billions of text assertions from the Web, and my research solved challenges in how to transform these noisy unstructured text assertions into Web scale actionable knowledge directly usable by people and in software.
I was supported by the Turing Center and an NDSEG fellowship.
Prior to UW, I worked at Lockheed Martin ATL's AI Lab where I developed software agents and also led research on scalable AI architectures.
I have Masters and Bachelors degrees from MIT in Computer Science.
My Master's Thesis under Professor Hal Abelson and Professor Dick Yue demonstrated an automated teaching algorithm that can effectively tailor presentations to learning styles.
My undergraduate research was in Commonsense Reasoning with Push Singh in Marvin Minsky's group at the MIT Media Lab. The project collected 100k+ commonsense statements from internet volunteers, and I developed techniques to reason over this data and rapidly collect more data.
Publications:
|
No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities Thomas Lin, Mausam, Oren Etzioni Conference on Empirical Methods in Natural Language Processing (EMNLP 2012) |
|
|
Mining Entity Types from Query Logs via User Intent Modeling Patrick Pantel, Thomas Lin, Michael Gamon 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012) |
|
|
Entity Linking at Web Scale Thomas Lin, Mausam, Oren Etzioni Knowledge Extraction Workshop (AKBC-WEKEX) at NAACL 2012 |
|
|
Active Objects: Actions for Entity-Centric Search Thomas Lin, Patrick Pantel, Michael Gamon, Anitha Kannan, Ariel Fuxman 21st International World Wide Web Conference (WWW 2012) |
|
|
No Search Result Left Behind: Branching Behavior with Browser Tabs Jeff Huang, Thomas Lin, Ryen White 5th ACM International Conference on Web Search and Data Mining (WSDM 2012) |
|
|
Commonsense from the Web: Relation Properties Thomas Lin, Mausam, Oren Etzioni AAAI Fall Symposium on Commonsense (CSK 2010) |
|
|
Identifying Functional Relations in Web Text Thomas Lin, Mausam, Oren Etzioni Conference on Empirical Methods in Natural Language Processing (EMNLP 2010) |
|
|
Machine Reading at the University of Washington Hoifung Poon, Janara Christensen, Pedro Domingos, Oren Etzioni, Raphael Hoffmann, Chloe Kiddon, Thomas Lin, Xiao Ling, Mausam, Alan Ritter, Stefan Schoenmackers, Stephen Soderland, Dan Weld, Fei Wu, and Congle Zhang Workshop on Formalisms and Methodology for Learning by Reading (FAM-LbR) at NAACL 2010 |
|
|
Identifying Interesting Assertions from the Web Thomas Lin, Oren Etzioni, James Fogarty 18th ACM Conference on Information and Knowledge Management (CIKM 2009) |
|
|
Filtering Information Extraction via User-Contributed Knowledge Thomas Lin, Oren Etzioni, James Fogarty User-Contributed Knowledge and Artificial Intelligence: An Evolving Synergy (WikiAI09) at IJCAI 2009 |
|
|
Open Mind Common Sense: Knowledge Acquisition from the General Public Push Singh, Thomas Lin, Erik T. Mueller, Grace Lim, Travell Perkins and Wan Li Zhu 1st International Conference on Ontologies, Databases, and Applications of Semantics for Large Scale Information Systems (ODBASE 2002) |
|
|
Analogical Inference over a Common Sense Database Thomas Lin 18th National Conference on Artificial Intelligence (AAAI 2002) |
TextRunner Salient Attributes (CSE 573) Word Sense Disambiguation with Images (w/Janara Christensen, Tony Fader) (CSE 510) Knowledge Guided Schema Discovery (w/Cynthia Matuszek) (CSE 544) Finding Interesting Tuples with Human Computation (KIA Meeting) Using AI to Identify Interesting Assertions (NPUC 2008) Concept Relator - Find the relation between two concepts Tic Tac Toe Program using MiniMax with Alpha-Beta Pruning Simple Eliza Implementation Context Aware Computing Final Project - MBTI Scheduler Intro to Artificial Intelligence Project #1 - Cgi/A* TA Allocator