A cost-effective lexical acquisition process for large-scale thesaurus translation

Abstract

Thesauri and controlled vocabularies facilitate access to digital collections by explicitly representing the underlying principles of organization. Translation of such resources into multiple languages is an important component for providing multilingual access. However, the specificity of vocabulary terms in most thesauri precludes fully-automatic translation using general-domain lexical resources. In this paper, we present an efficient process for leveraging human translations to construct domain-specific lexical resources. This process is illustrated on a thesaurus of 56,000 concepts used to catalog a large archive of oral histories. We elicited human translations on a small subset of concepts, induced a probabilistic phrase dictionary from these translations, and used the resulting resource to automatically translate the rest of the thesaurus. Two separate evaluations demonstrate the acceptability of the automatic translations and the cost-effectiveness of our approach.

A note on ontology localization

“…Much as in ontology localization, the goal here is to reuse existing thesauri or create multilingual systems for the purpose of indexing documents across languages. The issue of developing automatic approaches that can reduce the costs in translating thesauri into other languages is also crucial (Lin et al, 2009). In contrast to ontology localization, the goal in thesauri translation is to find a reasonable translation such that the thesaurus can support the same applications (e.g.…”