|
A word is a hypernym (in Greek υπερνύμιον, literally meaning 'extra name') if its meaning encompasses the meaning of another word of which it is a hypernym; a word that is more generic or broad than another given word. To achieve the meaning without a loanword, consider German Oberbegriff, lit. "Overconcept" thus "superterm". Therefore, another term for a hypernym is a superordinate. (In classic aristotelian logic, you have the unfashionable yet still correct "genera" for "hypernym" and "species" for "hyponym".) For example, vehicle denotes all the things that are separately denoted by the words train, chariot, dogsled, airplane, and automobile and is therefore a hypernym of each of those words. A hypernym is the opposite of a hyponym. For example, plant is hypernymic to flower whereas tulip is hyponymic to flower. Hypernymy is the semantic relation in which one word is the hypernym of another. Hypernymy, the relation words stand in when their extensions stand in the relation of class to subclass, should not be confused with holonymy which is the relation words stand in when the things that they denote stand in the relation of whole to part. A similar warning applies to hyponymy and meronymy.
Automatically finding hypernyms One of the first suggestions on how to find hypernym/hyponym pairs in a text came from Marti Hearst, who suggested looking at the output of a parser and taking all of the terms linked by constructions such as X and other Y; X could be considered a possible hyponym of Y. This method was extended by Snow et al, who developed an automated method of finding possible constructions that could signal such a pair. Their process works by taking hypernym/hyponym pairs from WordNet and finding many noun-noun pairs from a parsed corpus. They train a classifier to select those pairs of words that have a high probability of being hypernym pairs given the constructions which link the terms in the corpus. See also | ||||||||
|
| |||||||||
 |
|
| |