Overview of the Sixth Text REtrieval Conference (TREC-6)

By Ellen M. Voorhees, Donna K. Harman. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Distilled One-Shot Federated Learning (2020, methodology): “To show that DOSFL is not limited to image-based tasks, we test DOSFL to work on federated IMDB (sentiment analysis) [20] and federated TREC-6 (question classification) [32].”
A survey on the use of relevance feedback for information access systems (2003, background): “Other individual aspects that affect searching behaviour include the task the user is trying to achieve (Voorhees & Harman, 2000) and the searcher’s professional discipline (Fidel, 1991).”
Less is More Probabilistic Models for Retrieving Fewer Relevant Documents (2006, unknown): “For TREC-4 and TREC-6, multiple independent annotators were asked to make relevance judgments for the same set of topics, and over the same corpus [18, 7, 17].”
Improving the effectiveness of information retrieval with local context analysis (2000, background): “Recent TREC results show that local feedback can significantly improve retrieval effectiveness [Voorhees and Harman 1998].”
PubMed related articles: a probabilistic topic-based model for content similarity (2007, unknown): “That is, 80% of the time the pmra algorithm was merely reshuffing the top ten bm25 results– this is not unexpected, since bm25 already performs well and there's not much to be done in terms of improving the results in many cases.”
Relevant term suggestion in interactive web search based on contextual information in query session logs (2003, background): “The average length of a TREC topic description for conventional text retrieval was 15 tokens (Voorhees & Harman, 1998), while a Web search engine log analysis revealed that the average query length for a Web search was about 2.3 tokens (Silverstein et al., 1998).”
A comparison of user and system query performance predictions (2010, methodology): “Of the ﬁrst line, in an experiment in the late 1990’s [32], a number of IR researchers were asked to classify TREC topics as either easy , medium or hard for a newswire corpus they were familiar with.”
Assessing thesaurus-based query expansion using the UMLS Metathesaurus (2000, methodology): “Query expansion methods based on word-statistical approaches have been shown to be effective in the TREC experiments, which focus on government and newswire documents [9].”