Difference between revisions of "Hoffmann et al., ACL 2010"
From Cohen Courses
Jump to navigationJump to search| Line 9: | Line 9: | ||
[http://www.aclweb.org/anthology/P/P10/P10-1030.pdf ACL Anthology] | [http://www.aclweb.org/anthology/P/P10/P10-1030.pdf ACL Anthology] | ||
| − | [http://www.cs.washington.edu/affiliates/meetings/talks1011/hoffmann2010.pdf PPT | + | [http://www.cs.washington.edu/affiliates/meetings/talks1011/hoffmann2010.pdf PPT slides] |
== Summary == | == Summary == | ||
Revision as of 23:55, 29 September 2011
Contents
Citation
Raphael Hoffmann, Congle Zhang, and Daniel S. Weld. 2010. Learning 5000 relational extractors. In ACL '10 (Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics)
Online version
Summary
This is a paper introducing LUCHS, a self-supervised relations-specific IE system which learns 5025 relations with an average F1 score of 61%. The system applies dynamic lexicon learning.
