We envision an automatic knowledge base construction system consisting of three interrelated components. MADDEN is a knowledge extraction system applying statistical text analysis methods over database systems (DBMS) and massive parallel processing (MPP) frameworks; PROBKB performs probabilistic reasoning over the extracted knowledge to derive additional facts not existing in the original text corpus; CAMEL leverages human intelligence to reduce the uncertainty resulting from both the information extraction and probabilistic reasoning processes.
Authors:
Daisy Zhe Wang, Yang Chen, Sean Goldberg, Christan Grant, and Kun Li
Bibtex:
@inproceedings{Wang:2012:AKB:2391200.2391220,
author = {Wang, Daisy Zhe and Chen, Yang and Goldberg, Sean and Grant, Christan and Li, Kun},
title = {Automatic knowledge base construction using probabilistic extraction, deductive reasoning, and human feedback},
booktitle = {Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction},
series = {AKBC-WEKEX '12},
year = {2012},
location = {Montreal, Canada},
pages = {106--110},
numpages = {5},
url = {http://dl.acm.org/citation.cfm?id=2391200.2391220},
acmid = {2391220},
publisher = {Association for Computational Linguistics},
address = {Stroudsburg, PA, USA},
}