Comparing Web N-grams and Other Means of Identifying Named Entities in Corporate Blogs. Rachakonda, A., R., Srinivasa, S., Murthy, S., Palleti, A., R., & Ramya Krishna, Y. In Proceedings of SIGIR 2010 Web Ngrams Workshop, 2010.
Paper
Website abstract bibtex Identifying named entities is crucial to many text-analysis tasks. Several means of entity identification exist, but most means need to be improvised for use over informal text such as those found in corporate (internal) blogs. In this paper, we report on a comparison of four means part of speech, capitalized phrases with local n-grams and web n-grams, and a black box service to identifying entities in a real-life corporate blog system. Our experiments show that capitalized phrases provide the best means, and in particular, using local n-grams provide marginally better performance than using web n-grams.
@inProceedings{
title = {Comparing Web N-grams and Other Means of Identifying Named Entities in Corporate Blogs},
type = {inProceedings},
year = {2010},
keywords = {blog analytics,entity identification,text mining},
websites = {http://research.microsoft.com/en-us/events/webngram/sigir2010web_ngram_workshop_proceedings.pdf#page=51},
id = {fd1b7021-f481-3d00-b181-5a4e6be24611},
created = {2013-08-04T21:40:25.000Z},
file_attached = {true},
profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
last_modified = {2017-03-14T14:36:19.698Z},
tags = {named entities},
read = {true},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Rachakonda2010},
private_publication = {false},
abstract = {Identifying named entities is crucial to many text-analysis tasks. Several means of entity identification exist, but most means need to be improvised for use over informal text such as those found in corporate (internal) blogs. In this paper, we report on a comparison of four means part of speech, capitalized phrases with local n-grams and web n-grams, and a black box service to identifying entities in a real-life corporate blog system. Our experiments show that capitalized phrases provide the best means, and in particular, using local n-grams provide marginally better performance than using web n-grams.},
bibtype = {inProceedings},
author = {Rachakonda, Aditya Ramana and Srinivasa, Srinath and Murthy, Sudarshan and Palleti, Avinash Reddy and Ramya Krishna, Yella},
booktitle = {Proceedings of SIGIR 2010 Web Ngrams Workshop}
}
Downloads: 0
{"_id":"J4QBRbv3RcCpS8Hqr","bibbaseid":"rachakonda-srinivasa-murthy-palleti-ramyakrishna-comparingwebngramsandothermeansofidentifyingnamedentitiesincorporateblogs-2010","authorIDs":[],"author_short":["Rachakonda, A., R.","Srinivasa, S.","Murthy, S.","Palleti, A., R.","Ramya Krishna, Y."],"bibdata":{"title":"Comparing Web N-grams and Other Means of Identifying Named Entities in Corporate Blogs","type":"inProceedings","year":"2010","keywords":"blog analytics,entity identification,text mining","websites":"http://research.microsoft.com/en-us/events/webngram/sigir2010web_ngram_workshop_proceedings.pdf#page=51","id":"fd1b7021-f481-3d00-b181-5a4e6be24611","created":"2013-08-04T21:40:25.000Z","file_attached":"true","profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","tags":"named entities","read":"true","starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Rachakonda2010","private_publication":false,"abstract":"Identifying named entities is crucial to many text-analysis tasks. Several means of entity identification exist, but most means need to be improvised for use over informal text such as those found in corporate (internal) blogs. In this paper, we report on a comparison of four means part of speech, capitalized phrases with local n-grams and web n-grams, and a black box service to identifying entities in a real-life corporate blog system. Our experiments show that capitalized phrases provide the best means, and in particular, using local n-grams provide marginally better performance than using web n-grams.","bibtype":"inProceedings","author":"Rachakonda, Aditya Ramana and Srinivasa, Srinath and Murthy, Sudarshan and Palleti, Avinash Reddy and Ramya Krishna, Yella","booktitle":"Proceedings of SIGIR 2010 Web Ngrams Workshop","bibtex":"@inProceedings{\n title = {Comparing Web N-grams and Other Means of Identifying Named Entities in Corporate Blogs},\n type = {inProceedings},\n year = {2010},\n keywords = {blog analytics,entity identification,text mining},\n websites = {http://research.microsoft.com/en-us/events/webngram/sigir2010web_ngram_workshop_proceedings.pdf#page=51},\n id = {fd1b7021-f481-3d00-b181-5a4e6be24611},\n created = {2013-08-04T21:40:25.000Z},\n file_attached = {true},\n profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},\n group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},\n last_modified = {2017-03-14T14:36:19.698Z},\n tags = {named entities},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Rachakonda2010},\n private_publication = {false},\n abstract = {Identifying named entities is crucial to many text-analysis tasks. Several means of entity identification exist, but most means need to be improvised for use over informal text such as those found in corporate (internal) blogs. In this paper, we report on a comparison of four means part of speech, capitalized phrases with local n-grams and web n-grams, and a black box service to identifying entities in a real-life corporate blog system. Our experiments show that capitalized phrases provide the best means, and in particular, using local n-grams provide marginally better performance than using web n-grams.},\n bibtype = {inProceedings},\n author = {Rachakonda, Aditya Ramana and Srinivasa, Srinath and Murthy, Sudarshan and Palleti, Avinash Reddy and Ramya Krishna, Yella},\n booktitle = {Proceedings of SIGIR 2010 Web Ngrams Workshop}\n}","author_short":["Rachakonda, A., R.","Srinivasa, S.","Murthy, S.","Palleti, A., R.","Ramya Krishna, Y."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfdabac2-d7f2-3c5b-aa7a-06431c0ae35e/file/5d36ed3d-1ff8-1ac7-2dbb-f404e0327cee/2010-Comparing_Web_N-grams_and_Other_Means_of_Identifying_Named_Entities_in_Corporate_Blogs.pdf.pdf","Website":"http://research.microsoft.com/en-us/events/webngram/sigir2010web_ngram_workshop_proceedings.pdf#page=51"},"bibbaseid":"rachakonda-srinivasa-murthy-palleti-ramyakrishna-comparingwebngramsandothermeansofidentifyingnamedentitiesincorporateblogs-2010","role":"author","keyword":["blog analytics","entity identification","text mining"],"downloads":0,"html":""},"bibtype":"inProceedings","creationDate":"2020-02-06T23:48:12.231Z","downloads":0,"keywords":["blog analytics","entity identification","text mining"],"search_terms":["comparing","web","grams","means","identifying","named","entities","corporate","blogs","rachakonda","srinivasa","murthy","palleti","ramya krishna"],"title":"Comparing Web N-grams and Other Means of Identifying Named Entities in Corporate Blogs","year":2010}