NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Miao, Zhongtao, Zhao, Kaiyan, Nagata, Masaaki, Tsuruoka, Yoshimasa
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911714969124864
author Miao, Zhongtao
Zhao, Kaiyan
Nagata, Masaaki
Tsuruoka, Yoshimasa
author_facet Miao, Zhongtao
Zhao, Kaiyan
Nagata, Masaaki
Tsuruoka, Yoshimasa
contents 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. The dataset covers 16 languages and 75 translation directions in total, derived from approximately 10 million records of an English Wiktionary dump. The retrieval corpus of the search toolkit is also constructed from around 3 million cleaned records of the same dump. We then leverage the dataset and toolkit to train a translation agent via reinforcement learning (RL) and to evaluate the accuracy of neologism-aware machine translation. Furthermore, we propose an RL training framework featuring a novel reward design and an adaptive rollout generation strategy that exploits translation difficulty to further improve the translation quality of translation agents using our search toolkit.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03790
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
Miao, Zhongtao
Zhao, Kaiyan
Nagata, Masaaki
Tsuruoka, Yoshimasa
Computation and Language
Artificial Intelligence
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. The dataset covers 16 languages and 75 translation directions in total, derived from approximately 10 million records of an English Wiktionary dump. The retrieval corpus of the search toolkit is also constructed from around 3 million cleaned records of the same dump. We then leverage the dataset and toolkit to train a translation agent via reinforcement learning (RL) and to evaluate the accuracy of neologism-aware machine translation. Furthermore, we propose an RL training framework featuring a novel reward design and an adaptive rollout generation strategy that exploits translation difficulty to further improve the translation quality of translation agents using our search toolkit.
title NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.03790