Knowledge Modeling in Prior Art Search

Knowledge Modeling in Prior Art Search. Graf, E., Frommholz, I., Lalmas, M., & van Rijsbergen, K. In Cunningham, H., Hanbury, A., & Rüger, S., editors, Proceedings of the First Information Retrieval Facility Conference, IRFC 2010, volume 6107, pages 31–46, Berlin, Heidelberg, 2010. Springer Berlin Heidelberg. Series Title: Lecture Notes in Computer Science

Paper

Paper doi abstract bibtex

This study explores the benefits of integrating knowledge representations in prior art patent retrieval. Key to the introduced approach is the utilization of human judgment available in the form of classifications assigned to patent documents. The paper first outlines in detail how a methodology for the extraction of knowledge from such an hierarchical classification system can be established. Further potential ways of integrating this knowledge with existing Information Retrieval paradigms in a scalable and flexible manner are investigated. Finally based on these integration strategies the effectiveness in terms of recall and precision is evaluated in the context of a prior art search task for European patents. As a result of this evaluation it can be established that in general the proposed knowledge expansion techniques are particularly beneficial to recall and, with respect to optimizing field retrieval settings, further result in significant precision gains.

@inproceedings{Graf/etal:2010,
	address = {Berlin, Heidelberg},
	title = {Knowledge {Modeling} in {Prior} {Art} {Search}},
	volume = {6107},
	copyright = {All rights reserved},
	isbn = {978-3-642-13083-0},
	url = {http://www.springerlink.com/content/h33237742210026u/},
	doi = {10.1007/978-3-642-13084-7},
	abstract = {This study explores the benefits of integrating knowledge representations in prior art patent retrieval. Key to the introduced approach is the utilization of human judgment available in the form of classifications assigned to patent documents. The paper first outlines in detail how a methodology for the extraction of knowledge from such an hierarchical classification system can be established. Further potential ways of integrating this knowledge with existing Information Retrieval paradigms in a scalable and flexible manner are investigated. Finally based on these integration strategies the effectiveness in terms of recall and precision is evaluated in the context of a prior art search task for European patents. As a result of this evaluation it can be established that in general the proposed knowledge expansion techniques are particularly beneficial to recall and, with respect to optimizing field retrieval settings, further result in significant precision gains.},
	urldate = {2010-09-24},
	booktitle = {Proceedings of the {First} {Information} {Retrieval} {Facility} {Conference}, {IRFC} 2010},
	publisher = {Springer Berlin Heidelberg},
	author = {Graf, Erik and Frommholz, Ingo and Lalmas, Mounia and van Rijsbergen, Keith},
	editor = {Cunningham, Hamish and Hanbury, Allan and Rüger, Stefan},
	year = {2010},
	note = {Series Title: Lecture Notes in Computer Science},
	pages = {31--46},
	url_paper={https://api.zotero.org/users/9984690/publications/items/DUKCY9UE/file/view}
}

Downloads: 0

{"_id":"hu5ghM4mkMMM4sBx5","authorIDs":[],"author_short":["Graf, E.","Frommholz, I.","Lalmas, M.","van Rijsbergen, K."],"bibbaseid":"graf-frommholz-lalmas-vanrijsbergen-knowledgemodelinginpriorartsearch-2010","bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Berlin, Heidelberg","title":"Knowledge Modeling in Prior Art Search","volume":"6107","copyright":"All rights reserved","isbn":"978-3-642-13083-0","url":"http://www.springerlink.com/content/h33237742210026u/","doi":"10.1007/978-3-642-13084-7","abstract":"This study explores the benefits of integrating knowledge representations in prior art patent retrieval. Key to the introduced approach is the utilization of human judgment available in the form of classifications assigned to patent documents. The paper first outlines in detail how a methodology for the extraction of knowledge from such an hierarchical classification system can be established. Further potential ways of integrating this knowledge with existing Information Retrieval paradigms in a scalable and flexible manner are investigated. Finally based on these integration strategies the effectiveness in terms of recall and precision is evaluated in the context of a prior art search task for European patents. As a result of this evaluation it can be established that in general the proposed knowledge expansion techniques are particularly beneficial to recall and, with respect to optimizing field retrieval settings, further result in significant precision gains.","urldate":"2010-09-24","booktitle":"Proceedings of the First Information Retrieval Facility Conference, IRFC 2010","publisher":"Springer Berlin Heidelberg","author":[{"propositions":[],"lastnames":["Graf"],"firstnames":["Erik"],"suffixes":[]},{"propositions":[],"lastnames":["Frommholz"],"firstnames":["Ingo"],"suffixes":[]},{"propositions":[],"lastnames":["Lalmas"],"firstnames":["Mounia"],"suffixes":[]},{"propositions":["van"],"lastnames":["Rijsbergen"],"firstnames":["Keith"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Cunningham"],"firstnames":["Hamish"],"suffixes":[]},{"propositions":[],"lastnames":["Hanbury"],"firstnames":["Allan"],"suffixes":[]},{"propositions":[],"lastnames":["Rüger"],"firstnames":["Stefan"],"suffixes":[]}],"year":"2010","note":"Series Title: Lecture Notes in Computer Science","pages":"31–46","url_paper":"https://api.zotero.org/users/9984690/publications/items/DUKCY9UE/file/view","bibtex":"@inproceedings{Graf/etal:2010,\n\taddress = {Berlin, Heidelberg},\n\ttitle = {Knowledge {Modeling} in {Prior} {Art} {Search}},\n\tvolume = {6107},\n\tcopyright = {All rights reserved},\n\tisbn = {978-3-642-13083-0},\n\turl = {http://www.springerlink.com/content/h33237742210026u/},\n\tdoi = {10.1007/978-3-642-13084-7},\n\tabstract = {This study explores the benefits of integrating knowledge representations in prior art patent retrieval. Key to the introduced approach is the utilization of human judgment available in the form of classifications assigned to patent documents. The paper first outlines in detail how a methodology for the extraction of knowledge from such an hierarchical classification system can be established. Further potential ways of integrating this knowledge with existing Information Retrieval paradigms in a scalable and flexible manner are investigated. Finally based on these integration strategies the effectiveness in terms of recall and precision is evaluated in the context of a prior art search task for European patents. As a result of this evaluation it can be established that in general the proposed knowledge expansion techniques are particularly beneficial to recall and, with respect to optimizing field retrieval settings, further result in significant precision gains.},\n\turldate = {2010-09-24},\n\tbooktitle = {Proceedings of the {First} {Information} {Retrieval} {Facility} {Conference}, {IRFC} 2010},\n\tpublisher = {Springer Berlin Heidelberg},\n\tauthor = {Graf, Erik and Frommholz, Ingo and Lalmas, Mounia and van Rijsbergen, Keith},\n\teditor = {Cunningham, Hamish and Hanbury, Allan and Rüger, Stefan},\n\tyear = {2010},\n\tnote = {Series Title: Lecture Notes in Computer Science},\n\tpages = {31--46},\n\turl_paper={https://api.zotero.org/users/9984690/publications/items/DUKCY9UE/file/view}\n}\n\n\n\n","author_short":["Graf, E.","Frommholz, I.","Lalmas, M.","van Rijsbergen, K."],"editor_short":["Cunningham, H.","Hanbury, A.","Rüger, S."],"key":"Graf/etal:2010","id":"Graf/etal:2010","bibbaseid":"graf-frommholz-lalmas-vanrijsbergen-knowledgemodelinginpriorartsearch-2010","role":"author","urls":{"Paper":"http://www.springerlink.com/content/h33237742210026u/"," paper":"https://api.zotero.org/users/9984690/publications/items/DUKCY9UE/file/view"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero-mypublications/ifromm","creationDate":"2014-10-02T16:26:51.604Z","downloads":0,"keywords":[],"search_terms":["knowledge","modeling","prior","art","search","graf","frommholz","lalmas","van rijsbergen"],"title":"Knowledge Modeling in Prior Art Search","year":2010,"dataSources":["XtF8EMpyStxMyyKNA","fkSgDRzcDCXc6BaLu","zKsysPYoh4XuwpSS9","GfzAXsy4gLS4xSA9c","N4kJAiLiJ7kxfNsoh","JnthXBj8bcaW2wqpa"]}