TY - GEN
T1 - Unsupervised lexicon acquisition for HPSG-based relation extraction
AU - Rozenfeld, Benjamin
AU - Feldman, Ronen
PY - 2011
Y1 - 2011
N2 - The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the "Open IE" task, which is superior in accuracy and in quality of relation identification to the existing approaches.
AB - The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the "Open IE" task, which is superior in accuracy and in quality of relation identification to the existing approaches.
UR - http://www.scopus.com/inward/record.url?scp=84881067735&partnerID=8YFLogxK
U2 - 10.5591/978-1-57735-516-8/IJCAI11-316
DO - 10.5591/978-1-57735-516-8/IJCAI11-316
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84881067735
SN - 9781577355120
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 1890
EP - 1895
BT - IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence
T2 - 22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
Y2 - 16 July 2011 through 22 July 2011
ER -