A Scalable Architecture for Bilingual Lexicography
I. Dan Melamed · ScholarlyCommons (University of Pennsylvania) · 1997
Introduction SABLE (Scalable Architecture for Bilingual LExicography) is a turn-key system for producing clean broad-coverage translation lexicons from raw, unaligned parallel texts (bitexts). SABLE is designed to work for any text genre, in any pair of languages. As long as the input texts are mutual translations, the relative word order of the input languages makes no difference. No SABLE component makes any assumptions about the kinds of text units in the input: no component makes any use of sentence boundaries. SABLE was designed with the following features in mind: ffl Black box functionality: Automatic construction of translation lexicons requires only that the user provide the input bitexts and identify the two languages involved. ffl Robustness: SABLE copes well with omissions and inversions in translations. ffl Scalability: SABLE has been used successfully on bitexts larger than 130MB. ffl