TY - GEN
T1 - An iterative unsupervised learning method for information distillation
AU - Kamangar, Kamand
AU - Hakkani-Tür, Dilek
AU - Tur, Gokhan
AU - Levit, Michael
PY - 2008
Y1 - 2008
N2 - Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interest to the user. In this work, we propose an iterative un-supervised sentence extraction method to answer open-ended natural language queries about an event. The approach consists of finding the subset of sentences that are very likely to be relevant or irrelevant for the query from candidate documents, and iteratively training a classification model using these examples. Our results indicate that performance of the system may be improved by around 30% relative in terms of F-measure, by using the proposed method.
AB - Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interest to the user. In this work, we propose an iterative un-supervised sentence extraction method to answer open-ended natural language queries about an event. The approach consists of finding the subset of sentences that are very likely to be relevant or irrelevant for the query from candidate documents, and iteratively training a classification model using these examples. Our results indicate that performance of the system may be improved by around 30% relative in terms of F-measure, by using the proposed method.
KW - Information distillation
KW - Machine learning
KW - Question answering
KW - Unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=51449083410&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=51449083410&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2008.4518768
DO - 10.1109/ICASSP.2008.4518768
M3 - Conference contribution
AN - SCOPUS:51449083410
SN - 1424414849
SN - 9781424414840
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4949
EP - 4952
BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Y2 - 31 March 2008 through 4 April 2008
ER -