@article {15281, title = {An exploration of the principles underlying redundancy-based factoid question answering}, journal = {ACM Transactions on Information Systems}, volume = {25}, year = {2007}, month = {2007/04//}, abstract = {The so-called {\textquotedblleft}redundancy-based{\textquotedblright} approach to question answering represents a successful strategy for mining answers to factoid questions such as {\textquotedblleft}Who shot Abraham Lincoln?{\textquotedblright} from the World Wide Web. Through contrastive and ablation experiments with Aranea, a system that has performed well in several TREC QA evaluations, this work examines the underlying assumptions and principles behind redundancy-based techniques. Specifically, we develop two theses: that stable characteristics of data redundancy allow factoid systems to rely on external {\textquotedblleft}black box{\textquotedblright} components, and that despite embodying a data-driven approach, redundancy-based methods encode a substantial amount of knowledge in the form of heuristics. Overall, this work attempts to address the broader question of {\textquotedblleft}what really matters{\textquotedblright} and to provide guidance for future researchers.}, keywords = {Data redundancy, Web search}, isbn = {1046-8188}, doi = {10.1145/1229179.1229180}, url = {http://doi.acm.org/10.1145/1229179.1229180}, author = {Jimmy Lin} }