2 Hits in 12.0 sec

Robust Pseudo Feedback Estimation and HMM Passage Extraction: UIUC at TREC 2006 Genomics Track

Jing Jiang, Xin He, ChengXiang Zhai
2006 Text Retrieval Conference  
Acknowledgments We thank Xu Ling for judging the results to provide user relevance feedback. We thank Matt J. Wood and Fabien Campagne for providing a sentence locator tool.  ...  Introduction The University of Illinois at Urbana-Champaign (UIUC) participated in TREC 2006 Genomics Track.  ...  In our experiments, we used the Dirichlet prior smoothing method, and set µ to 1000 based on our preliminary experiments with the queries and documents from TREC 2005 Genomics Track.  ... 
dblp:conf/trec/JiangHZ06 fatcat:j562uxwu3rc4nimbficvuqls6i

Using language models in question answering [article]

Andreas Merkel, Universität Des Saarlandes, Universität Des Saarlandes
If this produces no results at all, answer candidates are extracted from the passage output produced using Indri. The Language Computer Corporation (LCC) also presented their work at TREC 2006.  ...  But, again in contrast to our observations, just pseudo-feedback helps to improve the performance.  ... 
doi:10.22028/d291-22488 fatcat:4yg7mip6szasxcr6aczqhdmarm