Translating Terminological Expressions in Knowledge Bases with Neural Machine Translation

TL;DR

This paper investigates neural machine translation for domain-specific terminological expressions in knowledge bases, focusing on challenges like vocabulary specificity and lack of context, and evaluates domain adaptation and external terminology injection.

Contribution

It introduces methods for domain adaptation and external terminology injection in neural translation models for knowledge base expressions, demonstrating their effectiveness.

Findings

Domain adaptation improves translation quality in medical and financial domains.

Subword models outperform word-based models for terminology translation.

External terminology injection benefits translation accuracy.

Abstract

Our work presented in this paper focuses on the translation of terminological expressions represented in semantically structured resources, like ontologies or knowledge graphs. The challenge of translating ontology labels or terminological expressions documented in knowledge bases lies in the highly specific vocabulary and the lack of contextual information, which can guide a machine translation system to translate ambiguous words into the targeted domain. Due to these challenges, we evaluate the translation quality of domain-specific expressions in the medical and financial domain with statistical as well as with neural machine translation methods and experiment domain adaptation of the translation models with terminological expressions only. Furthermore, we perform experiments on the injection of external terminological expressions into the translation systems. Through these experiments, we observed a significant advantage in domain adaptation for the domain-specific resource in the medical and financial domain and the benefit of subword models over word-based neural machine translation models for terminology translation.