Creating Lexical Resources for Endangered Languages

TL;DR

This paper presents methods to create lexical resources for endangered languages using minimal existing data, leveraging Wordnets and machine translation to build bilingual dictionaries and thesauruses.

Contribution

It introduces a resource-efficient approach that requires only one bilingual dictionary involving an endangered language and an intermediate language.

Findings

Effective construction of bilingual dictionaries for endangered languages.

Utilizes public Wordnets and machine translation to overcome resource scarcity.

Applicable to languages with limited existing linguistic resources.

Abstract

This paper examines approaches to generate lexical resources for endangered languages. Our algorithms construct bilingual dictionaries and multilingual thesauruses using public Wordnets and a machine translator (MT). Since our work relies on only one bilingual dictionary between an endangered language and an "intermediate helper" language, it is applicable to languages that lack many existing resources.