AI RESEARCH

NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning

arXiv CS.AI

ArXi:2601.03790v3 Announce Type: replace-cross Neologism-aware machine translation aims to translate source sentences containing neologisms into target languages. This field remains underexplored compared with general machine translation (MT). In this paper, we propose an agentic framework, NeoAMT, for neologism-aware machine translation equipped with a Wiktionary-based search toolkit. Specifically, we first construct a dedicated dataset for neologism-aware machine translation and build a search toolkit grounded in Wiktionary.