@inproceedings{ bradford_relationship_2006,
  title = {Relationship discovery in large text collections using latent semantic indexing},
  abstract = {This paper addresses the problem of information discovery in large collections of text. For users, one of the key problems in working with such collections is determining where to focus their attention. In selecting documents for examination, users must be able to formulate reasonably precise queries. Queries that are too broad will greatly reduce the efficiency of information discovery efforts by overwhelming the users with peripheral information. In order to formulate efficient queries, a mechanism is needed to automatically alert users regarding potentially interesting information contained within the collection. This paper presents the results of an experiment designed to test one approach to generation of such alerts. The technique of latent semantic indexing ({LSI}) is used to identify relationships among entities of interest. Entity extraction software is used to pre-process the text of the collection so that the {LSI} space contains representation vectors for named entities in addition to those for individual terms. In the {LSI} space, the cosine of the angle between the representation vectors for two entities captures important information regarding the degree of association of those two entities. For appropriate choices of entities, determining the entity pairs with the highest mutual cosine values yields valuable information regarding the contents of the text collection. The test database used for the experiment consists of 150,000 news articles. The proposed approach for alert generation is tested using a counterterrorism analysis example. The approach is shown to have significant potential for aiding users in rapidly focusing on information of potential importance in large text collections. The approach also has value in identifying possible use of aliases.},
  booktitle = {Proceedings of the Fourth Workshop on Link Analysis, Counterterrorism, and Security},
  author = {Bradford, R. B.},
  year = {2006},
  keywords = {latent_semantic_indexing}
}

{"_id":"scPR4bLQSYeqZeX92","authorIDs":[],"author_short":["Bradford, R.<nbsp>B."],"bibbaseid":"bradford-relationshipdiscoveryinlargetextcollectionsusinglatentsemanticindexing-2006","bibdata":{"abstract":"This paper addresses the problem of information discovery in large collections of text. For users, one of the key problems in working with such collections is determining where to focus their attention. In selecting documents for examination, users must be able to formulate reasonably precise queries. Queries that are too broad will greatly reduce the efficiency of information discovery efforts by overwhelming the users with peripheral information. In order to formulate efficient queries, a mechanism is needed to automatically alert users regarding potentially interesting information contained within the collection. This paper presents the results of an experiment designed to test one approach to generation of such alerts. The technique of latent semantic indexing (LSI) is used to identify relationships among entities of interest. Entity extraction software is used to pre-process the text of the collection so that the LSI space contains representation vectors for named entities in addition to those for individual terms. In the LSI space, the cosine of the angle between the representation vectors for two entities captures important information regarding the degree of association of those two entities. For appropriate choices of entities, determining the entity pairs with the highest mutual cosine values yields valuable information regarding the contents of the text collection. The test database used for the experiment consists of 150,000 news articles. The proposed approach for alert generation is tested using a counterterrorism analysis example. The approach is shown to have significant potential for aiding users in rapidly focusing on information of potential importance in large text collections. The approach also has value in identifying possible use of aliases.","author":["Bradford, R. B."],"author_short":["Bradford, R.<nbsp>B."],"bibtex":"@inproceedings{ bradford_relationship_2006,\n title = {Relationship discovery in large text collections using latent semantic indexing},\n abstract = {This paper addresses the problem of information discovery in large collections of text. For users, one of the key problems in working with such collections is determining where to focus their attention. In selecting documents for examination, users must be able to formulate reasonably precise queries. Queries that are too broad will greatly reduce the efficiency of information discovery efforts by overwhelming the users with peripheral information. In order to formulate efficient queries, a mechanism is needed to automatically alert users regarding potentially interesting information contained within the collection. This paper presents the results of an experiment designed to test one approach to generation of such alerts. The technique of latent semantic indexing ({LSI}) is used to identify relationships among entities of interest. Entity extraction software is used to pre-process the text of the collection so that the {LSI} space contains representation vectors for named entities in addition to those for individual terms. In the {LSI} space, the cosine of the angle between the representation vectors for two entities captures important information regarding the degree of association of those two entities. For appropriate choices of entities, determining the entity pairs with the highest mutual cosine values yields valuable information regarding the contents of the text collection. The test database used for the experiment consists of 150,000 news articles. The proposed approach for alert generation is tested using a counterterrorism analysis example. The approach is shown to have significant potential for aiding users in rapidly focusing on information of potential importance in large text collections. The approach also has value in identifying possible use of aliases.},\n booktitle = {Proceedings of the Fourth Workshop on Link Analysis, Counterterrorism, and Security},\n author = {Bradford, R. B.},\n year = {2006},\n keywords = {latent_semantic_indexing}\n}","bibtype":"inproceedings","booktitle":"Proceedings of the Fourth Workshop on Link Analysis, Counterterrorism, and Security","id":"bradford_relationship_2006","key":"bradford_relationship_2006","keywords":"latent_semantic_indexing","title":"Relationship discovery in large text collections using latent semantic indexing","type":"inproceedings","year":"2006","bibbaseid":"bradford-relationshipdiscoveryinlargetextcollectionsusinglatentsemanticindexing-2006","role":"author","urls":{},"keyword":["latent_semantic_indexing"],"downloads":0},"bibtype":"inproceedings","biburl":"http://bibbase.org/zotero/klaus.lepsky","creationDate":"2014-12-27T16:52:14.350Z","downloads":0,"keywords":["latent semantic indexing","latent_semantic_indexing"],"search_terms":["relationship","discovery","large","text","collections","using","latent","semantic","indexing","bradford"],"title":"Relationship discovery in large text collections using latent semantic indexing","year":2006,"dataSources":["toq45axpbC28psYaM"]}