This paper describes the functionality of MEAD, a comprehensive, public domain, open source, multidocument multilingual summariza-tion environment that has been thus far downloaded by more than 500 organizations. MEAD has been used in a variety of summarization applications ranging from summarization for mobile devices to Web page summarization within a… (More)
We present a large-scale meta evaluation of eight evaluation measures for both single-document and multi-document summarizers. To this end we built a corpus consisting of (a) 100 Million automatic summaries using six summarizers and baselines at ten summary lengths in both English and Chinese, (b) more than 10,000 manual abstracts and extracts, and (c) 200… (More)
The official evaluation of TREC-style Q&A systems is done manually, which is quite expensive and not scalable to web-based Q&A systems. An automatic evaluation technique is needed for dynamic Q&A systems. This paper presents a set of metrics that have been implemented in our web-based Q&A system, namely NSIR. It also shows the correlations between the… (More)
Web-based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five steps: query modulation, document retrieval, passage… (More)
Estrogen receptor α (ERα) is a marker predictive for response of breast cancers to endocrine therapy. About 30% of breast cancers, however, are hormone- independent because of lack of ERα expression. New strategies are needed for re-expression of ERα and sensitization of ER-negative breast cancer cells to selective ER modulators. The present report shows… (More)
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In this paper, we study how we can effectively use these existing search engines to mine the Web and discover the "correct" answers to factual natural language… (More)
We present the results of Michigan's participation in DUC 2003. Using mean length-adjusted coverage, we obtained the best score of all systems on task 4-question-focused summaries.