Use of OCR for Rapid Constrution of Bilingual Lexicons
Files
Publication or External Link
Date
Advisor
Citation
DRUM DOI
Abstract
This paper describes an approach to analyzing the lexical structure of OCRed bilingual dictionaries to construct resources suited for machine translation of low-density languages, where online resources are limited. A rule-based and an HMM-based method are used for rapid construction of MT lexicons based on systematic structural clues provided in the original dictionary. We evaluate the effectiveness of our techniques, concluding that: (1) the rule-based method performs better on dictionaries with a simple structure; (2) the stochastic method performs better on dictionaries with an enriched structure; (3) regardless of the degree of dictionary richness, the rule-based method gives better results for phrasal entries than for single-word entries; and (4) Our resulting bilingual lexicons are comprehensive enough to provide reasonable MT results when compared to human-constructed lexicons. (LAMP-TR-104) (CAR-TR-986) (UMIACS-TR-2003-78)