Estimation of word similarity
-----------------------------


Hello,

We kindly ask you to assist us in a psycholinguistic experiment, 
aimed at estimating the similarity of various words in the English 
language. The purpose of this experiment is to assign similarity scores 
to pairs of words, so that machine learning algorithms can be 
subsequently trained and adjusted using human-assigned scores.

Below is a list of pairs of words. For each pair, please assign 
a numerical similarity score between 0 and 10 (0 = words are totally 
unrelated, 10 = words are VERY closely related). By definition, 
the similarity of the word to itself should be 10. You may assign 
fractional scores (for example, 7.5).

Specific instructions:

1) The questionnaire starts on the next page.
2) Please fill in your full name at the beginning of the questionnaire. 
   We need the names to ensure individual estimations do not get mixed, 
   and to be able to contact you should any clarifications become necessary.
3) Please fill in the similarity scores in the appropriate column of 
   the table. To facilitate processing your questionnaire, please do not 
   print the document but rather type in the values in the table provided.
4) If you do not know the meaning of a particular word - please use 
   a dictionary, or ask a native English speaker.
5) Please DO NOT consult your friends on assigning the similarity scores  
   it is highly important that the scores you assign be independent of 
   someone elses assessment.
6) When estimating similarity of antonyms, consider them "similar"
   (i.e., belonging to the same domain or representing features of the same 
   concept), rather than "dissimilar".

If you have any questions or require further clarifications (or if you 
have a suggestion), please do not hesitate to contact us.

Thank you for your assistance !

