%0 Conference Paper %1 Mintz:2009:DSR:1690219.1690287 %A Mintz, Mike %A Bills, Steven %A Snow, Rion %A Jurafsky, Dan %B Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2 %C Stroudsburg, PA, USA %D 2009 %I Association for Computational Linguistics %K distantsupervision kallimachos nlp relations %P 1003--1011 %T Distant Supervision for Relation Extraction Without Labeled Data %U http://dl.acm.org/citation.cfm?id=1690219.1690287 %X Modern models of relation extraction for tasks like ACE are based on supervised learning of relations from small hand-labeled corpora. We investigate an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size. Our experiments use Freebase, a large semantic database of several thousand relations, to provide distant supervision. For each pair of entities that appears in some Freebase relation, we find all sentences containing those entities in a large unlabeled corpus and extract textual features to train a relation classifier. Our algorithm combines the advantages of supervised IE (combining 400,000 noisy pattern features in a probabilistic classifier) and unsupervised IE (extracting large numbers of relations from large corpora of any domain). Our model is able to extract 10,000 instances of 102 relations at a precision of 67.6%. We also analyze feature performance, showing that syntactic parse features are particularly helpful for relations that are ambiguous or lexically distant in their expression. %@ 978-1-932432-46-6

@inproceedings{Mintz:2009:DSR:1690219.1690287, abstract = {Modern models of relation extraction for tasks like ACE are based on supervised learning of relations from small hand-labeled corpora. We investigate an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size. Our experiments use Freebase, a large semantic database of several thousand relations, to provide distant supervision. For each pair of entities that appears in some Freebase relation, we find all sentences containing those entities in a large unlabeled corpus and extract textual features to train a relation classifier. Our algorithm combines the advantages of supervised IE (combining 400,000 noisy pattern features in a probabilistic classifier) and unsupervised IE (extracting large numbers of relations from large corpora of any domain). Our model is able to extract 10,000 instances of 102 relations at a precision of 67.6%. We also analyze feature performance, showing that syntactic parse features are particularly helpful for relations that are ambiguous or lexically distant in their expression.}, acmid = {1690287}, added-at = {2017-03-02T15:42:14.000+0100}, address = {Stroudsburg, PA, USA}, author = {Mintz, Mike and Bills, Steven and Snow, Rion and Jurafsky, Dan}, biburl = {https://www.bibsonomy.org/bibtex/2d96b180f4650d44d71d0eff25a62711c/albinzehe}, booktitle = {Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2}, description = {Distant supervision for relation extraction without labeled data}, interhash = {10d3718dbf071448f314a5380e0a6715}, intrahash = {d96b180f4650d44d71d0eff25a62711c}, isbn = {978-1-932432-46-6}, keywords = {distantsupervision kallimachos nlp relations}, location = {Suntec, Singapore}, numpages = {9}, pages = {1003--1011}, publisher = {Association for Computational Linguistics}, series = {ACL '09}, timestamp = {2017-03-02T15:42:14.000+0100}, title = {Distant Supervision for Relation Extraction Without Labeled Data}, url = {http://dl.acm.org/citation.cfm?id=1690219.1690287}, year = 2009 }