Book Search Experiments: Investigating IR Methods for the Indexing and Retrieval of Books

@incollection{citeulike:3112612, abstract = {Through mass-digitization projects and with the use of OCR technologies, digitized books are becoming available on the Web and in digital libraries. The unprecedented scale of these efforts, the unique characteristics of the digitized material as well as the unexplored possibilities of user interactions make full-text book search an exciting area of information retrieval (IR) research. Emerging research questions include: How appropriate and effective are traditional IR models when applied to books? What book specific features (e.g., back-of-book index) should receive special attention during the indexing and retrieval processes? How can we tackle scalability? In order to answer such questions, we developed an experimental platform to facilitate rapid prototyping of a book search system as well as to support large-scale tests. Using this system, we performed experiments on a collection of 10 000 books, evaluating the efficiency of a novel multi-field inverted index and the effectiveness of the BM25F retrieval model adapted to books, using book-specific fields.}, author = {Wu, Hengzhi and Kazai, Gabriella and Taylor, Michael }, citeulike-article-id = {3112612}, doi = {http://dx.doi.org/10.1007/978-3-540-78646-7\_23}, journal = {Advances in Information Retrieval}, keywords = {books, e-books, indexing--automatic, information\_retrieval, mass\_digitization}, pages = {234--245}, posted-at = {2008-08-12 19:57:18}, priority = {0}, title = {Book Search Experiments: Investigating IR Methods for the Indexing and Retrieval of Books}, url = {http://dx.doi.org/10.1007/978-3-540-78646-7\_23}, year = {2008} }

TY - CHAP ID - citeulike:3112612 L3 - citeulike-article-id:3112612 N2 - Through mass-digitization projects and with the use of OCR technologies, digitized books are becoming available on the Web and in digital libraries. The unprecedented scale of these efforts, the unique characteristics of the digitized material as well as the unexplored possibilities of user interactions make full-text book search an exciting area of information retrieval (IR) research. Emerging research questions include: How appropriate and effective are traditional IR models when applied to books? What book specific features (e.g., back-of-book index) should receive special attention during the indexing and retrieval processes? How can we tackle scalability? In order to answer such questions, we developed an experimental platform to facilitate rapid prototyping of a book search system as well as to support large-scale tests. Using this system, we performed experiments on a collection of 10 000 books, evaluating the efficiency of a novel multi-field inverted index and the effectiveness of the BM25F retrieval model adapted to books, using book-specific fields. JF - Advances in Information Retrieval EP - 245 TI - Book Search Experiments: Investigating IR Methods for the Indexing and Retrieval of Books SP - 234 KW - books KW - e-books KW - indexing--automatic KW - information_retrieval KW - mass_digitization AU - Wu, Hengzhi AU - Kazai, Gabriella AU - Taylor, Michael PY - 2008/// UR - http://dx.doi.org/10.1007/978-3-540-78646-7_23 ER -