NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning

• URL: http://arxiv.org/abs/2601.03790v2
• Date: Mon, 12 Jan 2026 15:01:07 GMT
• Title: NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
• Abstract summary: Neologism-aware machine translation aims to translate source sentences containing neologisms into target languages.<n>We propose an agentic framework, NeoAMT, for neologism-aware machine translation using a Wiktionary search tool.
• Score: 17.95065343652151
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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 using a Wiktionary search tool. Specifically, we first create a new dataset for neologism-aware machine translation and develop a search tool based on Wiktionary. The new dataset covers 16 languages and 75 translation directions and is derived from approximately 10 million records of an English Wiktionary dump. The retrieval corpus of the search tool is also constructed from around 3 million cleaned records of the Wiktionary dump. We then use it for training the translation agent with reinforcement learning (RL) and evaluating the accuracy of neologism-aware machine translation. Based on this, we also propose an RL training framework that contains a novel reward design and an adaptive rollout generation approach by leveraging "translation difficulty" to further improve the translation quality of translation agents using our search tool.

Related papers

• Creating Domain-Specific Translation Memories for Machine Translation Fine-tuning: The TRENCARD Bilingual Cardiology Corpus [0.0]
  The article introduces a semi-automatic TM preparation methodology leveraging primarily translation tools used by translators. The resulting corpus called TRENCARD Corpus has approximately 800,000 source words and 50,000 sentences.
  arXiv  Detail & Related papers  (2024-09-04T12:48:30Z)
• LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation [67.24113079928668]
  We present LexMatcher, a method for data curation driven by the coverage of senses found in bilingual dictionaries. Our approach outperforms the established baselines on the WMT2022 test sets.
  arXiv  Detail & Related papers  (2024-06-03T15:30:36Z)
• Machine Translation Models are Zero-Shot Detectors of Translation Direction [46.41883195574249]
  Detecting the translation direction of parallel text has applications for machine translation training and evaluation, but also has forensic applications such as resolving plagiarism or forgery allegations.<n>In this work, we explore an unsupervised approach to translation direction detection based on the simple hypothesis that $p(texttranslation|textoriginal)>p(textoriginal|texttranslation)$, motivated by the well-known simplification effect in translationese or machine-translationese.
  arXiv  Detail & Related papers  (2024-01-12T18:59:02Z)
• Extract and Attend: Improving Entity Translation in Neural Machine Translation [141.7840980565706]
  We propose an Extract-and-Attend approach to enhance entity translation in NMT. The proposed method is effective on improving both the translation accuracy of entities and the overall translation quality.
  arXiv  Detail & Related papers  (2023-06-04T03:05:25Z)
• Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models [55.35106713257871]
  We introduce DecoMT, a novel approach of few-shot prompting that decomposes the translation process into a sequence of word chunk translations. We show that DecoMT outperforms the strong few-shot prompting BLOOM model with an average improvement of 8 chrF++ scores across the examined languages.
  arXiv  Detail & Related papers  (2023-05-22T14:52:47Z)
• BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation [53.55009917938002]
  We propose to refine the mined bitexts via automatic editing. Experiments demonstrate that our approach successfully improves the quality of CCMatrix mined bitext for 5 low-resource language-pairs and 10 translation directions by up to 8 BLEU points.
  arXiv  Detail & Related papers  (2021-11-12T16:00:39Z)
• Extended Parallel Corpus for Amharic-English Machine Translation [0.0]
  It will be useful for machine translation of an under-resourced language, Amharic. We trained neural machine translation and phrase-based statistical machine translation models using the corpus.
  arXiv  Detail & Related papers  (2021-04-08T06:51:08Z)
• Constraint Translation Candidates: A Bridge between Neural Query Translation and Cross-lingual Information Retrieval [45.88734029123836]
  We propose a novel approach to alleviate problems by limiting the open target vocabulary search space of QT to a set of important words mined from search index database. The proposed methods are exploited and examined in a real-word CLIR system--Aliexpress e-Commerce search engine.
  arXiv  Detail & Related papers  (2020-10-26T15:27:51Z)
• SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task [111.91077204077817]
  We participated in four translation directions of three language pairs: English-Chinese, English-Polish, and German-Upper Sorbian. Based on different conditions of language pairs, we have experimented with diverse neural machine translation (NMT) techniques. In our submissions, the primary systems won the first place on English to Chinese, Polish to English, and German to Upper Sorbian translation directions.
  arXiv  Detail & Related papers  (2020-10-11T00:40:05Z)
• It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information [90.35685796083563]
  Cross-mutual information (XMI) is an asymmetric information-theoretic metric of machine translation difficulty. XMI exploits the probabilistic nature of most neural machine translation models. We present the first systematic and controlled study of cross-lingual translation difficulties using modern neural translation systems.
  arXiv  Detail & Related papers  (2020-05-05T17:38:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.