machine translation

8 items

NEWSGoogle for Developers (YouTube)·10h ago

Introducing Gemini 3.5 Live Translate

Google introduced Gemini 3.5 Live Translate, a new feature enabling real-time translation. This innovation aims to enhance multilingual communication instantly.

Google AI Gemini machine translation AI

RESEARCHarXiv CS.CL·5/7/2026

Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages

Nsanku is a systematic benchmark evaluating the zero-shot machine translation performance of 19 LLMs across 43 Ghanaian languages. It utilizes Bible sentences and metrics like BLEU and chrF, with gemini-2.5-flash achieving the highest overall average score.

LLMs Benchmarking machine translation Low-resource languages

RESEARCHarXiv CS.CL·4/14/2026

Should We be Pedantic About Reasoning Errors in Machine Translation?

This research identifies and quantifies reasoning errors in machine translation across multiple language pairs, using an automated annotation protocol. Experiments with interventions on reasoning traces suggest that strong corrections improve error resolution, though with mixed gains in overall translation quality.

Reasoning Errors machine translation Translation Quality Interventions

RESEARCHarXiv CS.CL·22d ago

Fluency and Faithfulness in Human and Machine Literary Translation

This research investigates the balance between fluency and faithfulness in literary translation, comparing human, Google Translate, and TranslateGemma performance across 106 novels in 16 source languages. It reveals a consistent negative correlation between fluency and faithfulness, particularly for human and Google Translate, and indicates that segment length significantly impacts automatic evaluation.

Literary Translation Translation Evaluation Natural Language Processing machine translation

RESEARCHarXiv CS.CL·4/22/2026

Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation

This paper introduces a novel in-context learning approach for low-resource Coptic to English machine translation, augmenting inputs with syntactic information from Universal Dependencies parses. Combining this syntactic data with dictionary-based glosses achieves significant gains and sets a new state-of-the-art.

universal-dependencies Natural Language Processing machine translation in-context learning

RESEARCHarXiv CS.CL·5/7/2026

The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translation

This paper systematically investigates the impact of joint and disjoint vocabularies on knowledge transfer in multilingual neural machine translation (MNMT). Experiments show that extensive vocabulary overlaps, language relatedness, and domain-match lead to better performance, even in out-of-domain setups.

neural networks knowledge transfer NLP machine translation

RESEARCHarXiv CS.CL·4/6/2026

An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages

Este estudo empírico investiga o aprendizado em contexto (ICL) de muitos exemplos para tradução automática de inglês para dez idiomas de baixo recurso. Os achados mostram que o ICL se torna mais eficaz com o aumento do número de exemplos, e a recuperação baseada em BM25 melhora substancialmente a eficiência dos dados.

LLMs Many-Shot Learning NLP machine translation

ARTICLEDEV.to AI·4/15/2026

When one translation isn't enough

This content explores scenarios where a single translation might be insufficient. It discusses the need for more complex approaches to effective communication across different cultural and linguistic contexts.

NLP localization machine translation AI