| abstract |
A method facilitates generating a number of candidate passages from a corpus that answer an input query, and finds the correct resulting answer by collecting supporting evidence from multiple passages. By analyzing all retrieved passages and that passage's metadata in parallel, an output plurality of data structures including candidate answers based upon the analyzing is generated. Then, by each of a plurality of parallel operating modules, supporting passage retrieval operations are performed upon the set of candidate answers, and for each candidate answer, the data corpus is traversed to find those passages having candidate answer in addition to query terms. All candidate answers are automatically scored causing the supporting passages by a plurality of scoring modules, each producing a module score that is processed to determine one or more query answers. A query response is then generated for delivery to a user based on the one or more query answers. |