%0 Journal Article
%A FANG NAN
%D 2026
%C Berlin, Germany
%I Peter Lang Verlag
%J Journal of Translation Studies
%@ 2673-6934
%N 1
%V 6
%T A Bilingual Knowledge Base for Maritime Translation Teaching: Design, Development and Application
%R 10.3726/JTS012026.4
%U https://www.peterlang.com/document/1737156
%X This study addresses three interrelated challenges in maritime translation education—the scarcity of authentic teaching materials, inconsistent terminology use, and students’ insufficient domain knowledge—by developing a bilingual knowledge base tailored to the training of translation of maritime subject-matter. Built on a diachronic bilingual corpus derived from the Report on China’s Shipping Development (2012–2024), the knowledge base integrates corpus linguistics methodologies with process-oriented pedagogy. Using a Python-based technology stack, the system incorporates TF-IDF vector retrieval, sentence-level semantic alignment, and term standardization preprocessing. Its two core functions—industry background knowledge query and maritime terminology bilingual reference—are designed to scaffold students’ cognitive preparation and terminology decision-making during translation tasks. An evaluation based on 20 representative query prompts demonstrates that the knowledge base reliably retrieves structured contextual information and supplies authentic, context-bound examples of term usage. By illustrating how corpus resources and AI techniques can be synergistically deployed to meet domain-specific, scenario-driven instructional needs, this study provides a replicable model for pedagogical resource development and instructional design in specialized translation education.
%K knowledge base, corpus, artificial intelligence, process-oriented translator training