Democratizing Neural Machine Translation with OPUS-MT

• URL: http://arxiv.org/abs/2212.01936v3
• Date: Tue, 4 Jul 2023 11:55:20 GMT
• Title: Democratizing Neural Machine Translation with OPUS-MT
• Abstract summary: This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools. We discuss our on-going mission of increasing language coverage and translation quality, and also describe on-going work on the development of modular translation models.
• Score: 56.21988248821684
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. We discuss our on-going mission of increasing language coverage and translation quality, and also describe on-going work on the development of modular translation models and speed-optimized compact solutions for real-time translation on regular desktops and small devices.

Related papers

• CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation [16.295305195753723]
  We develop a family of small language models (0.8B, 1.4B, 3.3B, and 7B parameters) specialized for Japanese-English bidirectional translation.<n>We evaluate our models on WMT and real-world translation benchmarks across business, legal, medical, financial, and patent domains.
  arXiv  Detail & Related papers  (2026-06-19T13:28:59Z)
• Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models [1.4582633500696451]
  This paper explores the transformative role of Agent AI and LangGraph in advancing the automation and effectiveness of machine translation (MT) Agents are modular components designed to perform specific tasks, such as translating between particular languages. LangGraph, a graph-based framework built on LangChain, simplifies the creation and management of these agents.
  arXiv  Detail & Related papers  (2024-12-05T01:45:12Z)
• LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models [50.259006481656094]
  We present a novel interactive application aimed towards understanding the internal mechanisms of large vision-language models. Our interface is designed to enhance the interpretability of the image patches, which are instrumental in generating an answer. We present a case study of how our application can aid in understanding failure mechanisms in a popular large multi-modal model: LLaVA.
  arXiv  Detail & Related papers  (2024-04-03T23:57:34Z)
• MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki [46.62437145754009]
  We present the MAMMOTH toolkit, a framework for training massively multilingual modular machine translation systems at scale. We showcase its efficiency across clusters of A100 and V100 NVIDIA GPUs, and discuss our design philosophy and plans for future information.
  arXiv  Detail & Related papers  (2024-03-12T11:32:30Z)
• adaptNMT: an open-source, language-agnostic development environment for Neural Machine Translation [2.648836772989769]
  adaptNMT is designed for both technical and non-technical users who work in the field of machine translation. The application is built upon the widely-adopted OpenNMT ecosystem. To support eco-friendly research in the NLP space, a green report also flags the power consumption and kgCO$_2$ emissions generated during model development.
  arXiv  Detail & Related papers  (2024-03-04T12:10:17Z)
• Developing automatic verbatim transcripts for international multilingual meetings: an end-to-end solution [0.0]
  This paper presents an end-to-end solution for the creation of fully automated conference meeting transcripts and their machine translations into various languages. This tool has been developed at the World Intellectual Property Organization (WIPO) using in-house developed speech-to-text (S2T) and machine translation (MT) components.
  arXiv  Detail & Related papers  (2023-09-27T12:16:15Z)
• A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation [13.426403221815063]
  This paper surveys the landscape of language-and-vision pre-training from the lens of multimodal machine translation. We summarize the common architectures, pre-training objectives, and datasets from literature and conjecture what further is needed to make progress on multimodal machine translation.
  arXiv  Detail & Related papers  (2023-06-12T15:56:10Z)
• Translation Word-Level Auto-Completion: What can we achieve out of the box? [6.241494296494433]
  We investigate the possibility of using pre-trained models and out-of-the-box features from available libraries. We introduce our open-source API, based on CTranslate2, to serve translations, auto-suggestions, and auto-completions.
  arXiv  Detail & Related papers  (2022-10-23T17:58:01Z)
• Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations [75.73028056136778]
  We show how to practically build MNMT systems that serve arbitrary X-Y translation directions. We also examine our proposed approach in an extremely large-scale data setting to accommodate practical deployment scenarios.
  arXiv  Detail & Related papers  (2022-06-30T02:18:15Z)
• The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task [92.5087402621697]
  This paper describes the submission of our end-to-end YiTrans speech translation system for the IWSLT 2022 offline task. The YiTrans system is built on large-scale pre-trained encoder-decoder models. Our final submissions rank first on English-German and English-Chinese end-to-end systems in terms of the automatic evaluation metric.
  arXiv  Detail & Related papers  (2022-06-12T16:13:01Z)
• Beyond English-Centric Multilingual Machine Translation [74.21727842163068]
  We create a true Many-to-Many multilingual translation model that can translate directly between any pair of 100 languages. We build and open source a training dataset that covers thousands of language directions with supervised data, created through large-scale mining. Our focus on non-English-Centric models brings gains of more than 10 BLEU when directly translating between non-English directions while performing competitively to the best single systems of WMT.
  arXiv  Detail & Related papers  (2020-10-21T17:01:23Z)
• DiDi's Machine Translation System for WMT2020 [51.296629834996246]
  We participate in the translation direction of Chinese->English. In this direction, we use the Transformer as our baseline model. As a result, our submission achieves a BLEU score of $36.6$ in Chinese->English.
  arXiv  Detail & Related papers  (2020-10-16T06:25:48Z)

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.