TY - GEN
T1 - Improved fully unsupervised parsing with zoomed learning
AU - Reichart, Roi
AU - Rappoport, Ari
PY - 2010
Y1 - 2010
N2 - We introduce a novel training algorithm for unsupervised grammar induction, called Zoomed Learning. Given a training set T and a test set S, the goal of our algorithm is to identify subset pairs Ti, Si of T and S such that when the unsupervised parser is trained on a training subset T i its results on its paired test subset Si are better than when it is trained on the entire training set T. A successful application of zoomed learning improves overall performance on the full test set S. We study our algorithm's effect on the leading algorithm for the task of fully unsupervised parsing (Seginer, 2007) in three different English domains, WSJ, BROWN and GENIA, and show that it improves the parser F-score by up to 4.47%.
AB - We introduce a novel training algorithm for unsupervised grammar induction, called Zoomed Learning. Given a training set T and a test set S, the goal of our algorithm is to identify subset pairs Ti, Si of T and S such that when the unsupervised parser is trained on a training subset T i its results on its paired test subset Si are better than when it is trained on the entire training set T. A successful application of zoomed learning improves overall performance on the full test set S. We study our algorithm's effect on the leading algorithm for the task of fully unsupervised parsing (Seginer, 2007) in three different English domains, WSJ, BROWN and GENIA, and show that it improves the parser F-score by up to 4.47%.
UR - http://www.scopus.com/inward/record.url?scp=80053228417&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:80053228417
SN - 1932432868
SN - 9781932432862
T3 - EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 684
EP - 693
BT - EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2010
Y2 - 9 October 2010 through 11 October 2010
ER -