TRAPHO allows to carry out a phonetic ("fuzzy") search of words, especially of proper names.
By applying the approx. 100 language specific rules within TRAPHO to a given word, this word is translated into an abstract representation. This representation is than compared with the representations of the words in which the user wants to search. Names, whose correct spelling is unknown, or variants of such names or variants produced by typing errors, can be found.
For instance Deutschland can be detected, even if the spelling in the document is teutschland or duutschland. If someone searches for Kournikova, but types in Cornigowa this hit can be found.
In contrast to other phonetic systems, TRAPHO is based on the following idea: the spelling variants of a words depends on the language of the searcher. A German speaker for instance would write a name which he/she heart in a different way than an English speaker. If a German speaker searches for Achternbusch, he/she would normally key in the same characters, but an English speaker would probably type Ekternbush, because this is the way this name is pronounced in English.
Therefore, TRAPHO has different language versions (German, French, English, Latin, Italian, Dutch, Norwegian and Spanish). Different language versions can be combined in a cascading way for an even broader search.
Each language version consists itself of two different phonetic functions, which differs from each other in the strictness of the applied rules, thus making TRAPHO a powerful extra tool within EXTRAKT's whole spectrum of linguistic features.
We made also tests with the list of the players of the German Soccer league (Bundesliga). Soem results can be found here!