Enhancing Scientific Discourse: Machine Translation for the Scientific Domain
This work provides domain-specific resources for improving machine translation in scientific communication, but the approach is incremental as it applies existing fine-tuning methods to new corpora.
The authors created parallel and monolingual corpora for scientific text translation across Spanish-English, French-English, and Portuguese-English, and fine-tuned NMT systems to improve translation quality in specialized domains. Fine-tuning yielded BLEU score improvements of up to 5 points over general-purpose models.
The increasing volume of scientific research necessitates effective communication across language barriers. Machine translation (MT) offers a promising solution for accessing international publications. However, the scientific domain presents unique challenges due to its specialized vocabulary and complex sentence structures. In this paper, we present the development of a collection of parallel and monolingual corpora for the scientific domain. The corpora target the language pairs Spanish-English, French-English, and Portuguese-English. For each language pair, we create a large general scientific corpus as well as four smaller corpora focused on the domains of: Cancer Research, Energy Research, Neuroscience, and Transportation research. To evaluate the quality of these corpora, we utilize them for fine-tuning general-purpose neural machine translation (NMT) systems. We provide details regarding the corpus creation process, the fine-tuning strategies employed, and we conclude with the evaluation results.