Information extraction (IE) can identify a set of relations from free text to support question answering (QA). Until recently, IE systems were domain-specific and needed a combination of manual engineering and supervised learning to adapt to each target domain. A new paradigm, Open IE operates on large text corpora without any manual tagging of relations, and indeed without any pre-specified relations. Due to its open-domain and open-relation nature, Open IE is purely textual and is unable to relate the surface forms to an ontology, if known in advance. We explore the steps needed to adapt Open IE to a domain-specific ontology and demonstrate our approach of mapping domain-independent tuples to an ontology using domains from DARPA's Machine Reading Project. Our system achieves precision over 0.90 from as few as 8 training examples for an NFL-scoring domain.
%0 Journal Article
%1 SoderlandRoofEtAl10aimag
%A Soderland, Stephen
%A Roof, Brendan
%A Qin, Bo
%A Xu, Shi
%A Mausam,
%A Etzioni, Oren
%D 2010
%J AI Magazine
%K 01801 aaai paper ai language processing information retrieval ontology learn answer zzz.iui
%N 3
%P 93--102
%R 10.1609/aimag.v31i3.2305
%T Adapting Open Information Extraction to Domain-Specific Relations
%V 31
%X Information extraction (IE) can identify a set of relations from free text to support question answering (QA). Until recently, IE systems were domain-specific and needed a combination of manual engineering and supervised learning to adapt to each target domain. A new paradigm, Open IE operates on large text corpora without any manual tagging of relations, and indeed without any pre-specified relations. Due to its open-domain and open-relation nature, Open IE is purely textual and is unable to relate the surface forms to an ontology, if known in advance. We explore the steps needed to adapt Open IE to a domain-specific ontology and demonstrate our approach of mapping domain-independent tuples to an ontology using domains from DARPA's Machine Reading Project. Our system achieves precision over 0.90 from as few as 8 training examples for an NFL-scoring domain.
@article{SoderlandRoofEtAl10aimag,
abstract = {Information extraction (IE) can identify a set of relations from free text to support question answering (QA). Until recently, IE systems were domain-specific and needed a combination of manual engineering and supervised learning to adapt to each target domain. A new paradigm, Open IE operates on large text corpora without any manual tagging of relations, and indeed without any pre-specified relations. Due to its open-domain and open-relation nature, Open IE is purely textual and is unable to relate the surface forms to an ontology, if known in advance. We explore the steps needed to adapt Open IE to a domain-specific ontology and demonstrate our approach of mapping domain-independent tuples to an ontology using domains from DARPA's Machine Reading Project. Our system achieves precision over 0.90 from as few as 8 training examples for an NFL-scoring domain.},
added-at = {2012-05-30T10:54:16.000+0200},
author = {Soderland, Stephen and Roof, Brendan and Qin, Bo and Xu, Shi and Mausam and Etzioni, Oren},
biburl = {https://www.bibsonomy.org/bibtex/204dd5aadfa897511a903c31b50b741d0/flint63},
doi = {10.1609/aimag.v31i3.2305},
file = {AAAI online:2010/SoderlandRoofEtAl10aimag.pdf:PDF},
groups = {public},
interhash = {650fe0e0ac00b0d4fb0c7a8799fdf359},
intrahash = {04dd5aadfa897511a903c31b50b741d0},
issn = {0738-4602},
journal = {AI Magazine},
keywords = {01801 aaai paper ai language processing information retrieval ontology learn answer zzz.iui},
number = 3,
pages = {93--102},
timestamp = {2018-04-16T12:01:55.000+0200},
title = {Adapting Open Information Extraction to Domain-Specific Relations},
username = {flint63},
volume = 31,
year = 2010
}