Generating Links by Mining Quotations Export

@inproceedings{okanSchilit2008:miningLinks, abstract = {Scanning books, magazines, and newspapers has become a widespread activity because people believe that much of the worlds information still resides off-line. In general after works are scanned they are indexed for search and processed to add links. This paper describes a new approach to au- tomatically add links by mining popularly quoted passages. Our technique connects elements that are semantically rich, so strong relations are made. Moreover, link targets point within a work, facilitating navigation. This paper makes three contributions. We describe a scalable algorithm for mining repeated word sequences from extremely large text corpora. Second, we present techniques that filter and rank the repeated sequences for quotations. Third, we present a new user interface for navigating across and within works in the collection using quotation links. Our system has been run on a digital library of over 1 million books and has been used by thousands of people.}, address = {Pittsburg, Pennsylvania}, author = {Kolak, Okan and Schilit, Bill N.}, booktitle = {Proceedings of the 19th conference on Hypertext and hypermedia}, citeulike-article-id = {2838127}, day = {19}, keywords = {data\_mining, document\_linking, ht08, information\_extraction}, month = {June}, posted-at = {2008-05-27 20:31:02}, priority = {2}, title = {Generating Links by Mining Quotations}, year = {2008} }

TY - CONF ID - okanSchilit2008:miningLinks L3 - citeulike-article-id:2838127 N2 - Scanning books, magazines, and newspapers has become a widespread activity because people believe that much of the worlds information still resides off-line. In general after works are scanned they are indexed for search and processed to add links. This paper describes a new approach to au- tomatically add links by mining popularly quoted passages. Our technique connects elements that are semantically rich, so strong relations are made. Moreover, link targets point within a work, facilitating navigation. This paper makes three contributions. We describe a scalable algorithm for mining repeated word sequences from extremely large text corpora. Second, we present techniques that filter and rank the repeated sequences for quotations. Third, we present a new user interface for navigating across and within works in the collection using quotation links. Our system has been run on a digital library of over 1 million books and has been used by thousands of people. AD - Pittsburg, Pennsylvania TI - Generating Links by Mining Quotations T2 - Proceedings of the 19th conference on Hypertext and hypermedia KW - data_mining KW - document_linking KW - ht08 KW - information_extraction AU - Kolak, Okan AU - Schilit, Bill PY - 2008/06/19/21 ER -