Automatic paraphrase acquisition from news articles. Shinyama, Y.; Sekine, S.; and Sudo, K. In Proceedings of the second international conference on Human Language Technology Research, of HLT '02, pages 313-318, 2002. Morgan Kaufmann Publishers Inc..
Automatic paraphrase acquisition from news articles [pdf]Paper  Automatic paraphrase acquisition from news articles [link]Website  abstract   bibtex   
Paraphrases play an important role in the variety and complexity of natural language documents. However, they add to the difficulty of natural language processing. Here we describe a procedure for obtaining paraphrases from news articles. Articles derived from different newspapers can contain paraphrases if they report the same event on the same day. We exploit this feature by using Named Entity recognition. Our approach is based on the assumption that Named Entities are preserved across paraphrases. We applied our method to articles of two domains and obtained notable examples. Although this is our initial attempt at automatically extracting paraphrases from a corpus, the results are promising.
@inProceedings{
 title = {Automatic paraphrase acquisition from news articles},
 type = {inProceedings},
 year = {2002},
 identifiers = {[object Object]},
 pages = {313-318},
 websites = {http://portal.acm.org/citation.cfm?doid=1289189.1289218},
 publisher = {Morgan Kaufmann Publishers Inc.},
 institution = {Morgan Kaufmann Publishers Inc. San Francisco, CA, USA},
 series = {HLT '02},
 id = {b101c795-ed80-33b7-97cf-69fefc2bd8f6},
 created = {2012-02-28T00:51:15.000Z},
 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,paraphrasing},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Shinyama2002},
 private_publication = {false},
 abstract = {Paraphrases play an important role in the variety and complexity of natural language documents. However, they add to the difficulty of natural language processing. Here we describe a procedure for obtaining paraphrases from news articles. Articles derived from different newspapers can contain paraphrases if they report the same event on the same day. We exploit this feature by using Named Entity recognition. Our approach is based on the assumption that Named Entities are preserved across paraphrases. We applied our method to articles of two domains and obtained notable examples. Although this is our initial attempt at automatically extracting paraphrases from a corpus, the results are promising.},
 bibtype = {inProceedings},
 author = {Shinyama, Yusuke and Sekine, Satoshi and Sudo, Kiyoshi},
 booktitle = {Proceedings of the second international conference on Human Language Technology Research}
}
Downloads: 0