Search & Media Sciences is responsible for constantly improving the experience of Yahoo! customers on our search and media sites. Our scientists combine a diverse set of scientific disciplines including information retrieval, machine learning, statistical modeling, NLP and data-mining to create new algorithms and data models for query and content understanding, recommendation, ranking and presenting results. Our scientists work with the engineering and product groups, and deliver innovation into Yahoo search and media products impacting millions of users across the world, thousands of times every second.

Disciplines & Areas of Expertise

Scientific FieldsScientific Disciplines include Information Retrival, Machine Learning, Data & Text Mining and Natural Language Processing.     Learn More
Areas of ExpertiseAreas of Expertise include Ranking, Classification, Information Extraction and Recommended Systems.     Learn more

Team

Publications

"Dancing with the Stars", NBA Games, Politics: An exploration of Twitter users' response to events, Popescu, Ana-Maria, and Pennacchiotti Marco , ICWSM, 07/2011, (2011) Abstract
A machine-learning approach to Twitter user classification, Pennacchiotti, Marco, and Popescu Ana-Maria , ICWSM, 07/2011, (2011) Abstract
Learning recurrent event queries for Web search, Zhang, Ruiqiang, Konda Yuki, Dong Anlei, Kolari Pranam, and Chang Yi , EMNLP'2010, 08/2010, Boston, (2010)
Optimizing unified loss for web ranking specialization, Li, Fan, Li Xin, Bian Jiang, and Zheng Zhaohui , The 19th ACM international conference on Information and knowledge management (CIKM2010), (2010)
Ranking specialization for web search: a divide-and-conquer approach by using topical RankSVM, Zha, Hongyuan, Bian Jiang, Li Xin, Li Fan, and Zheng Zhaohui , The 19th international conference on World wide web (WWW2010), 2010, (2010)
Online Domain-Adaptation of a Pre-Trained Cascade of Classifiers, Jain, Vidit, and Learned-Miller Erik , CVPR 2011, Colorado Springs, USA, (2011) Abstract
Learning to Re-Rank: Query-Dependent Image Re-Ranking Using Click Data, Jain, Vidit, and Varma Manik , WWW 2011, Hyderabad, India, (2011) Abstract
Detecting Controversial Events from Twitter, Popescu, Ana-Maria, and Pennacchiotti Marco , CIKM, (2010) Abstract
Graph Mining for the Web, Donato, Debora, and Gionis Aristides , Managing and Mining Graph Data , (2010)
Graph Structures and Algorithms for Query-Log Analysis, Donato, Debora , CIE 2010, 07/2010, (2010)
Coniunge et Impera: Multiple-graph mining for Query-log analysis, Bordino, Ilaria, Donato Debora, and Baeza-Yates Ricardo , ECML PKDD, 09/2010, Barcelona, Spain, (2010)
Query Similarity by Projecting the Query-Flow Graph, Bordino, Ilaria, Castillo Carlo, Donato Debora, and Gionis Aristides , SIGIR, 07/2010, Geneva, Switzerland, (2010)
Session Based Click Features for Recency Ranking, Inagaki, Yoshiyuki, Sadagopan Narayanan, Dupret Georges, Liao Ciya, Dong Anlei, Chang Yi, and Zheng Zhaohui , the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2010), (2010) Abstract
IntervalRank - Isotonic Regression with Listwise and Pairwise Constraints, Moon, Taesup, Smola Alex, Chang Yi, and Zheng Zhaohui , Third ACM International Conference on Web Search and Data Mining (WSDM), 02/2010, Brooklyn, NY, (2010)
Efficiently Evaluating Complex Boolean Expressions, Fontoura, Marcus, Sadanandan Suhas, Shanmugasundaram Jayavel, Vassilvitski Sergei, Vee Erik, Venkatesan Srihari, and Zien Jason , SIGMOD, 06/2010, (2010)
To combine discriminative classifiers, Lee, Chi-Hoon , KDD, Washington D.C., USA., p.To appear, (2010)
A large-scale active learning system for topical categorization on the web, Rajan, Suju, Yankov Dragomir, Gaffney Scott, and Ratnaparkhi Adwait , The 19th International World Wide Web Conference, 2010, Raleigh, North Carolina, USA, (2010)
Surface Form Resolution Based on Wikipedia, Zhou, Yiping, Nie Lan, and Gaffney Scott , The 23rd International Conference on Computational Linguistics (COLING 2010), Beijing, China, (Submitted)
Quantifying the Limits and Success of Extractive Summarization Systems Across Domains, Ceylan, Hakan, Mihalcea Rada, Ozertem Umut, Lloret Elena, and Palomar Manuel , NAACL-HLT, 06/2010, (2010) Abstract
The Effects of Time on Query Flow Graph-based Models for Query Suggestion, Baraglia, Ranieri, Perego Raffaele, Silvestri Fabrizio, Castillo Carlo, Donato Debora, and Nardini Franco Maria , 9th international conference on Adaptivity, Personalization and Fusion of Heterogeneous Information (RIAO), 04/2010, Paris, France, (2010)
Do you want to take notes? Identifying research missions in Yahoo! Search Pad, Donato, Debora, Bonchi Francesco, Chi Tom, and Maarek Yoelle , WWW 2010: Proceedings of the 19th international conference on World Wide Web, 04/2010, Raleigh, (2010)
Active Learning for Ranking through Expected Loss Optimization, Long, Bo, Chapelle Olivier, Zhang Ya, Chang Yi, Zheng Zhaohui, and Tseng Belle , Proceedings of the 33th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'10), Geneva, Switzerland, (2010)
A user behavior model for average precision and its generalization to graded judgments, Dupret, Georges, and Piwowarski Benjamin , sigir, 07/2010, geneva, switzerland, (2010) Abstract
Twitter: A Starting Point for Controversy Detection, Pennacchiotti, Marco, and Popescu Ana Maria , Workshop on Social Media, NAACL, 2010, (2010)
Semantic Lexicon Adaptation for Use in Query Interpretation, Popescu, Ana Maria, Pantel Patrick, and Mishne Gilad , WWW, 2010, Raleigh, NC, (2010)