Automatically Creating a Large Number of New Bilingual Dictionaries

TL;DR

This paper introduces methods to automatically generate numerous bilingual dictionaries for low-resource languages using a single input dictionary, Wordnets, and machine translation, expanding language resources significantly.

Contribution

The authors present a novel approach that leverages minimal resources to create many new bilingual dictionaries, especially for endangered and resource-poor languages.

Findings

Created 48 new bilingual dictionaries from 5 initial ones.

Generated 30 language pairs unsupported by major MT services.

Applicable to any language with a Wordnet or English as one language.

Abstract

This paper proposes approaches to automatically create a large number of new bilingual dictionaries for low-resource languages, especially resource-poor and endangered languages, from a single input bilingual dictionary. Our algorithms produce translations of words in a source language to plentiful target languages using available Wordnets and a machine translator (MT). Since our approaches rely on just one input dictionary, available Wordnets and an MT, they are applicable to any bilingual dictionary as long as one of the two languages is English or has a Wordnet linked to the Princeton Wordnet. Starting with 5 available bilingual dictionaries, we create 48 new bilingual dictionaries. Of these, 30 pairs of languages are not supported by the popular MTs: Google and Bing.