Building Better Search Engines by Measuring Search Quality

Search engines help users locate information within large stores of content developed for human consumption. For example, users expect Web search engines to direct searchers to websites based on the content of the site rather than the site address, and future video search engines to return video clips based on the actions recorded in the clip rather than filenames and donor tags. Search engines are developed using standard sets of realistic test cases that allow developers to measure the relative effectiveness of alternative approaches. The NIST Text Retrieval Conference (TREC) project has been instrumental in creating the necessary infrastructure to measure the quality of search results for more than 20 years, and has thus helped fuel the recent explosive growth in search-related technologies. This article is part of a special issue on NIST contributions to IT.