Query answering usually assumes that the Asker is looking for a single correct answer to the question. When retrieving a textual answer this is often the case, but when searching for numeric answers, there are additional considerations. In particular, numbers often have units associated with them, and the Asker may not care whether the raw answer is in feet or meters. Also, numbers usually denote a precision. In a few cases, the precision may be explicit, but normally, there is an implied precision associated with every number. Finally, we can associate different reliability levels to different sources. We experimentally show that, in the context of conflicting answers from multiple sources, numeric query accuracy can be improved by taking advantage of units, precision, and the reliability of sources.

Websites vary in terms of reliability. One could assume that NASA's website will be very accurate for Astronomy questions. Wikipedia is less accurate but is still more accurate than a generic Google search. In this research we ask a large number of "factoid" questions to several different search engines. We collect those responses and determine the correctness of each candidate answer. The answers are grouped by website source, and are compared to other websites to infer website correctness.

No abstract

Most web search engines today are geared towards providing a list of relevant websites, along with snippets of text from each website that are relevant to the user's search text. Some of them may also provide specific answers to the user's question. This paper explores techniques for combining many candidate answers into a small set of answers, when it is likely that there is more than one correct answer. We describe and test new algorithms that collect and consolidate candidate answers from many different websites using paired support, reinforcing the ranking factor of those candidate answers that co-occur as pairs across multiple website domains.

No abstract