Web object retrieval Export

@inproceedings{Nie2007, abstract = {The primary function of current Web search engines is essentially relevance ranking at the document level. However, myriad structured information about real-world objects is embedded in static Web pages and online Web databases. Document-level information retrieval can unfortunately lead to highly inaccurate relevance ranking in answering object-oriented queries. In this paper, we propose a paradigm shift to enable searching at the object level. In traditional information retrieval models, documents are taken as the retrieval units and the content of a document is considered reliable. However, this reliability assumption is no longer valid in the object retrieval context when multiple copies of information about the same object typically exist. These copies may be inconsistent because of diversity of Web site qualities and the limited performance of current information extraction techniques. If we simply combine the noisy and inaccurate attribute information extracted from different sources, we may not be able to achieve satisfactory retrieval performance. In this paper, we propose several language models for Web object retrieval, namely an unstructured object retrieval model, a structured object retrieval model, and a hybrid model with both structured and unstructured retrieval features. We test these models on a paper search engine and compare their performances. We conclude that the hybrid model is the superior by taking into account the extraction errors at varying levels.}, address = {New York, NY, USA}, author = {Nie, Zaiqing and Ma, Yunxiao and Shi, Shuming and Wen, Ji-Rong and Ma, Wei-Ying}, booktitle = {WWW '07: Proceedings of the 16th international conference on World Wide Web}, citeulike-article-id = {2696971}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1242572.1242584}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1242572.1242584}, doi = {10.1145/1242572.1242584}, isbn = {978-1-59593-654-7}, keywords = {cleaning, duplicate, entity, information\_extraction, language-model, search}, location = {Banff, Alberta, Canada}, pages = {81--90}, posted-at = {2008-04-21 16:48:06}, priority = {3}, publisher = {ACM}, title = {Web object retrieval}, url = {http://dx.doi.org/10.1145/1242572.1242584}, year = {2007} }

TY - CONF ID - Nie2007 L3 - citeulike-article-id:2696971 N2 - The primary function of current Web search engines is essentially relevance ranking at the document level. However, myriad structured information about real-world objects is embedded in static Web pages and online Web databases. Document-level information retrieval can unfortunately lead to highly inaccurate relevance ranking in answering object-oriented queries. In this paper, we propose a paradigm shift to enable searching at the object level. In traditional information retrieval models, documents are taken as the retrieval units and the content of a document is considered reliable. However, this reliability assumption is no longer valid in the object retrieval context when multiple copies of information about the same object typically exist. These copies may be inconsistent because of diversity of Web site qualities and the limited performance of current information extraction techniques. If we simply combine the noisy and inaccurate attribute information extracted from different sources, we may not be able to achieve satisfactory retrieval performance. In this paper, we propose several language models for Web object retrieval, namely an unstructured object retrieval model, a structured object retrieval model, and a hybrid model with both structured and unstructured retrieval features. We test these models on a paper search engine and compare their performances. We conclude that the hybrid model is the superior by taking into account the extraction errors at varying levels. CY - Banff, Alberta, Canada SN - 978-1-59593-654-7 AD - New York, NY, USA EP - 90 TI - Web object retrieval PB - ACM T2 - WWW '07: Proceedings of the 16th international conference on World Wide Web SP - 81 KW - cleaning KW - duplicate KW - entity KW - information_extraction KW - language-model KW - search AU - Nie, Zaiqing AU - Ma, Yunxiao AU - Shi, Shuming AU - Wen, Ji-Rong AU - Ma, Wei-Ying PY - 2007/// UR - http://dx.doi.org/10.1145/1242572.1242584 ER -