Dictionary Alignment by Rewrite-based Entry Translation

Abstract

In this document we describe the process of aligning two standard
monolingual dictionaries: a Portuguese language dictionary and a Galician synonym dictionary. The main goal of the project is to provide an online dictionary that can show, in parallel, definitions
and synonyms in Portuguese and Galician for a specific word, written
in Portuguese or Galician.
    
These two languages are very close to each other, and that is the main reason we expect this idea to be viable. The main drawback is the lack of a good and free translation dictionary between these two languages, namely, a dictionary that can cover lexicons with more than one hundred thousand different words.
    
To solve this issue we defined a translation function, based on  substitutions, that is able to achieve an F_1 score of 0.88 on a manually verified dictionary of nine thousand words. Using this same  translation function to align a Portuguese--Galician dictionary we obtained almost 50% of the dictionary lexicon (more than eighty thousand words) alignment.