Learn More
Passage retrieval is an important component common to many question answering systems. Because most evaluations of question answering systems focus on end-to-end performance, comparison of common components becomes difficult. To address this shortcoming, we present a quantitative evaluation of various passage retrieval algorithms for question answering,(More)
This paper describes the START Information Server built at the MIT Arti cial Intelligence Laboratory Available on the World Wide Web since December the START Server provides users with access to multi media information in response to questions for mulated in English Over the last years the START Server answered hundreds of thousands of questions from users(More)
We present an approach for automatically learning paraphrases from aligned monolingual corpora. Our algorithm works by generalizing the syntactic paths between corresponding anchors in aligned sentence pairs. Compared to previous work, structural paraphrases generated by our algorithm tend to be much longer on average, and are capable of capturing(More)
A bstr act: Question answering systems have proven to be helpful to users because they can provide succinct answers that do not require users to wade through a large number of documents. However, despite recent advances in the underlying question answering technology, the problem of designing effective interfaces has been largely unexplored. We conducted a(More)
Although the World Wide Web contains a tremendous amount of information, the lack of uniform structure makes finding the right knowledge difficult. A solution is to turn the Web into a “virtual database” and to access it through natural language. We built Omnibase, a system that integrates heterogeneous data sources using an object– property–value model.(More)
Definition questions represent a largely unexplored area of question answering—they are different from factoid questions in that the goal is to return as many relevant “nuggets” of information about a concept as possible. We describe a multi-strategy approach to answering such questions using a database constructed offline with surface patterns, a Webbased(More)
We present a strategy for answering fact-based natural language questions that is guided by a characterization of real-world user queries. Our approach, implemented in a system called Aranea, extracts answers from the Web using two different techniques: <i>knowledge annotation</i> and <i>knowledge mining</i>. Knowledge annotation is an approach to answering(More)