Text Information Management and Analysis Group

Software

• Extended rstandard retrieval models for appropriate lower-bounding of TF (BM25+, Dir+, PL2+, and others)
• Positional Language Models
• Positional Relevance Models
• Opinosis Opinion/Text Summarizer (Ganesan & Zhai COLING 2010)
• UCAIR Toolbar (an Internet Explorer plug-in to support client-side personalized search developed by the UCAIR team)
• Search logger (browser plug-in to log your web search history) developed by Bin Tan : IE version (.msi), Firefox version (.xpi) See here for usage.
• GeneRecognizer: A gene/protein name recognition tool, trained on the annotated data from BioCreative I Task 1A (written by Jing Jiang)
• A Tokenization Tool for Biomedical Text (written by Jing Jiang)
• C++ wrapper for WordNet's C API written by Bin Tan (only supports HYPERPTR currently; easily finds the most frequent synset by tagged count)

Data Sets

• Data set for Latent Aspect Rating Analysis used in (Wang & Zhai KDD 2011) and (Wang & Zhai KDD 2010).
• Data set for online discussion structure learning used in (Wang & Zhai SIGIR 2011).
• Data set for forum post retrieval used in (Duan & Zhai ECIR 2011).
• Data Set for Implicit Feedback used in (Shen et al. SIGIR 05).
• Data Set for Evolutionary Theme Pattern Discovery used in (Mei & Zhai KDD 2005).
• Data Set for Multi-Aspect Review Assignment used in (Karimzadehgan & Zhai CIKM 2008).
• Data Set for Contrastive Summarization used in (Kim & Zhai CIKM 2009)
• Data Set for Opinion Matching
• Data Set for Opinosis used in (Ganesan & Zhai COLING 2010)

Presentations

• MIAS 2011 Tutorial on IR and Web Information Access
• HLT 2007 Tutorial on LM for IR