66
6
archive
disk0/00/00/00/66
2009-04-06 19:10:24
2009-04-28 08:57:07
2009-04-06 19:10:24
conference_item
show
0
-
Bollegala
Danushka
The University of Tokyo
-
Matsuo
Yutaka
The University of Tokyo
-
Ishizuka
Mitsuru
The University of Tokyo
Measuring the Similarity between Implicit Semantic Relations from the Web
pub
public
paper
Measuring the similarity between semantic relations that hold among
entities is an important and necessary step in various Web related
tasks such as relation extraction, information retrieval and analogy
detection. For example, consider the case in which a person knows
a pair of entities (e.g. Google, YouTube), between which a partic-
ular relation holds (e.g. acquisition). The person is interested in
retrieving other such pairs with similar relations (e.g. Microsoft,
Powerset). Existing keyword-based search engines cannot be ap-
plied directly in this case because, in keyword-based search, the
goal is to retrieve documents that are relevant to the words used in
a query – not necessarily to the relations implied by a pair of words.
We propose a relational similarity measure, using a Web search en-
gine, to compute the similarity between semantic relations implied
by two pairs of words. Our method has three components: repre-
senting the various semantic relations that exist between a pair of
words using automatically extracted lexical patterns, clustering the
extracted lexical patterns to identify the different patterns that ex-
press a particular semantic relation, and measuring the similarity
between semantic relations using a metric learning approach. We
evaluate the proposed method in two tasks: classifying semantic
relations between named entities, and solving word-analogy ques-
tions. The proposed method outperforms all baselines in a relation
classification task with a statistically significant average precision
score of 0.74. Moreover, it reduces the time taken by Latent Relational Analysis to process 374 word-analogy questions from 9 days
to less than 6 hours, with an SAT score of 51%.
2009-04
651-651
18th International World Wide Web Conference
Madrid, Spain
April 20th-24th, 2009
conference
TRUE
66
4
66
1
application/pdf
en
public
p651.pdf
published
p651.pdf
1134577
http://www2009.eprints.org/66/1/p651.pdf
284
3
66
2
application/pdf
en
public
paper_373_slides.pdf
presentation
paper_373_slides.pdf
1363386
http://www2009.eprints.org/66/2/paper_373_slides.pdf