CSE8801 TWS: Topics in Web Search

1. Query Annotation

   Annotation is a problem with broad applications: image and video annotation, bio-sequence annotation, document annotation and query annotation to name a few. These applications have their similarities and differences, but it may be useful to look at them from a unified perspective. We focus on query annotation which should include:
   • query classification
   • named entity recognition
   • query tagging
   • automatic generation of training data
   • Extracting Structured Information from User Queries with Semi-Supervised Conditional Random Fields

   • Named Entity Recognition in Query

   • Named Entity Mining from Click-Through Data Using Weakly Supervised Latent Dirichlet Allocation

   • Collective Annotation of Wikipedia Entities in Web Text

   • Improving Classification Accuracy Using Automatically Extracted Training Data

2. Learning to Rank

   • Risky Business: Modeling and Exploiting Uncertainty in Information Retrieval

   • Learning to Rank for Quantity Consensus Queries

   • Portfolio Theory of Information Retrieval

   • Document Selection Methodologies for Efficient and Effective Learning-to-Rank

3. CQA

   • Ranking Community Answers by Modeling Question-Answer Relationships via Analogical Reasoning

   • A Syntactic Tree Matching Approach to Finding Similar Questions in Community-based QA Services

4. Context

   • Predicting User Interests from Contextual Information

   • Mining Broad Latent Query Aspects from Search Sessions

   • Mining Rich Session Context to Improve Web Search

5. CF

   • Fast Nonparametric Matrix Factorization for Large-scale Collaborative Filtering

   • Learning to Recommend with Social Trust Ensemble

   • Collaborative Filtering with Temporal Dynamics

   • TANGENT: A Novel, "Suprise Me" Recommendation Algorithm

6. Advertising

   • Large-Scale Behavioral Targeting

   • Audience Selection for On-line Brand Advertising: Privacy-friendly Social Network Targeting

   • Catching the Drift: Learning Broad Matches from Clickthrough Data

   • Predicting Bounce Rates in Sponsored Search Advertisements

7. Social Network

   • Finding a Team of Experts in Social Networks

   • Characterizing Individual Communication Patterns

8. Query Expansion

   • RelevanceBased Language Models

   • Regularized Estimation of Mixture Models for Robust PseudoRelevance Feedback

   • Estimating Robust Query Models with Convex Optimization