Difference between revisions of "JAIR Analogical Mapping (State of the art)"

From ACL Wiki
Jump to navigation Jump to search
(Created page with "* analogical mapping between two sets of words * 20 mapping problems: 10 science analogies, 10 common metaphors * typically about 7 words per set * available from [http://jair...")
 
 
(2 intermediate revisions by the same user not shown)
Line 4: Line 4:
 
* available from [http://jair.org/media/2693/live-2693-4214-jair.txt JAIR]
 
* available from [http://jair.org/media/2693/live-2693-4214-jair.txt JAIR]
 
* task described [http://jair.org/papers/paper2693.html here]
 
* task described [http://jair.org/papers/paper2693.html here]
 +
* see also: [[Analogy (State of the art)]]
  
 
== Sample question ==
 
== Sample question ==
Line 10: Line 11:
  
 
'''Solution:''' {solar system -> atom, sun -> nucleus, planet -> electron, mass -> charge, attracts -> attracts, revolves -> revolves, gravity -> electromagnetism}
 
'''Solution:''' {solar system -> atom, sun -> nucleus, planet -> electron, mass -> charge, attracts -> attracts, revolves -> revolves, gravity -> electromagnetism}
 +
 +
== Table of results ==
 +
 +
{| border="1" cellpadding="5" cellspacing="1" width="100%"
 +
|-
 +
! Algorithm
 +
! Reference for algorithm
 +
! Reference for experiment
 +
! Type
 +
! Correct
 +
|-
 +
| LIN+POS
 +
| Lin (1998)
 +
| Turney (2008)
 +
| WordNet-based
 +
| 76.8%
 +
|-
 +
| human
 +
| human
 +
| Turney (2008)
 +
| human
 +
| 87.6%
 +
|-
 +
| LRME
 +
| Turney (2008)
 +
| Turney (2008)
 +
| corpus-based
 +
| 91.5%
 +
|}
 +
 +
== References ==
 +
 +
Lin, D. (1998). [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.55.1832&rep=rep1&type=pdf An information-theoretic definition of similarity]. ''Proceedings of the 15th International Conference on Machine Learning (ICML-98)'', Madison, WI, pp. 296-304.
 +
 +
Turney, P.D. (2008), [http://jair.org/papers/paper2693.html The latent relation mapping engine: Algorithm and experiments], ''Journal of Artificial Intelligence Research (JAIR)'', 33, 615-655.
 +
 +
 +
[[Category:State of the art]]
 +
[[Category:Analogy]]

Latest revision as of 14:11, 25 January 2017

  • analogical mapping between two sets of words
  • 20 mapping problems: 10 science analogies, 10 common metaphors
  • typically about 7 words per set
  • available from JAIR
  • task described here
  • see also: Analogy (State of the art)

Sample question

Problem: Map {planet, attracts, revolves, sun, gravity, solar system, mass} to {revolves, atom, attracts, electromagnetism, nucleus, charge, electron}

Solution: {solar system -> atom, sun -> nucleus, planet -> electron, mass -> charge, attracts -> attracts, revolves -> revolves, gravity -> electromagnetism}

Table of results

Algorithm Reference for algorithm Reference for experiment Type Correct
LIN+POS Lin (1998) Turney (2008) WordNet-based 76.8%
human human Turney (2008) human 87.6%
LRME Turney (2008) Turney (2008) corpus-based 91.5%

References

Lin, D. (1998). An information-theoretic definition of similarity. Proceedings of the 15th International Conference on Machine Learning (ICML-98), Madison, WI, pp. 296-304.

Turney, P.D. (2008), The latent relation mapping engine: Algorithm and experiments, Journal of Artificial Intelligence Research (JAIR), 33, 615-655.

Retrieved from "https://aclweb.org/aclwiki/index.php?title=JAIR_Analogical_Mapping_(State_of_the_art)&oldid=11767"