ConceptNet 3: a Flexible, Multilingual Semantic Network for Common Sense Knowledge
C. Havasi, R. Speer, and J. Alonso. Recent Advances in Natural Language Processing, Borovets, Bulgaria, (September 2007)
Abstract
The Open Mind Common Sense project has been
collecting common-sense knowledge from volunteers
on the Internet since 2000. This knowledge
is represented in a machine-interpretable semantic
network called ConceptNet.
We present ConceptNet 3, which improves the
acquisition of new knowledge in ConceptNet and
facilitates turning edges of the network back into
natural language. We show how its modular design
helps it adapt to different data sets and
languages. Finally, we evaluate the content of
ConceptNet 3, showing that the information it
contains is comparable with WordNet and the
Brandeis Semantic Ontology.
%0 Conference Paper
%1 paper:havasi:2007
%A Havasi, Catherine
%A Speer, Robert
%A Alonso, Jason
%B Recent Advances in Natural Language Processing
%C Borovets, Bulgaria
%D 2007
%K 2007 commonsense evaluation goals knowledge networks tools
%T ConceptNet 3: a Flexible, Multilingual Semantic Network for Common Sense Knowledge
%X The Open Mind Common Sense project has been
collecting common-sense knowledge from volunteers
on the Internet since 2000. This knowledge
is represented in a machine-interpretable semantic
network called ConceptNet.
We present ConceptNet 3, which improves the
acquisition of new knowledge in ConceptNet and
facilitates turning edges of the network back into
natural language. We show how its modular design
helps it adapt to different data sets and
languages. Finally, we evaluate the content of
ConceptNet 3, showing that the information it
contains is comparable with WordNet and the
Brandeis Semantic Ontology.
@inproceedings{paper:havasi:2007,
abstract = {The Open Mind Common Sense project has been
collecting common-sense knowledge from volunteers
on the Internet since 2000. This knowledge
is represented in a machine-interpretable semantic
network called ConceptNet.
We present ConceptNet 3, which improves the
acquisition of new knowledge in ConceptNet and
facilitates turning edges of the network back into
natural language. We show how its modular design
helps it adapt to different data sets and
languages. Finally, we evaluate the content of
ConceptNet 3, showing that the information it
contains is comparable with WordNet and the
Brandeis Semantic Ontology.},
added-at = {2008-06-13T13:33:49.000+0200},
address = {Borovets, Bulgaria},
author = {Havasi, Catherine and Speer, Robert and Alonso, Jason},
biburl = {https://www.bibsonomy.org/bibtex/208bdc0c326abf022173437181e57d44f/mschuber},
booktitle = {Recent Advances in Natural Language Processing},
interhash = {f7f2941c795e66d60a7d7183ef324876},
intrahash = {08bdc0c326abf022173437181e57d44f},
keywords = {2007 commonsense evaluation goals knowledge networks tools},
month = {September},
timestamp = {2008-09-09T12:54:39.000+0200},
title = {ConceptNet 3: a Flexible, Multilingual Semantic Network for Common Sense Knowledge},
year = 2007
}