paper-with-me

홈 › Papers

Marian: Cost-effective High-Quality Neural Machine Translation in C++

2018-05-30 · WS 2018 7 · Marcin Junczys-Dowmunt, Kenneth Heafield, Hieu Hoang, Roman Grundkiewicz, Anthony Aue

This paper describes the submissions of the "Marian" team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task.

📄 PDF Abstract BibTeX arXiv:1805.12096

Code (1)

MindSpore-scientific-2/code-14/tree/main/marian mindspore

Tasks

CPUGPUMachine TranslationTranslationVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Marian: Fast Neural Machine Translation in C++

2018-04-01 · ACL 2018 7 · Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang 외

We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs. Marian is written entirely in C++. We descr…

DecoderMachine TranslationTranslation

PyMarian: Fast Neural Machine Translation and Evaluation in Python

2024-08-15 · Thamme Gowda, Roman Grundkiewicz, Elijah Rippeth, Matt Post 외

The deep learning language of choice these days is Python; measured by factors such as available libraries and technical support, it is hard to beat. At the same time, software written in lower-level programming language…

Machine TranslationNMTTranslation

MarianCG: a code generation transformer model inspired by machine translation

2022-11-22 · Journal of Engineering and Applied Science 2022 11 · Ahmed S. Soliman, Mayada M. Hadhoud, Samir I. Shaheen

The idea that computers can build their own programs is extremely significant, and many researchers are working on this challenge. Code generation is described as the process of generating executable code that can be run…

Code GenerationCode TranslationLanguage ModelingLanguage Modelling+3

Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language

2021-07-16 · Peter Jansen, Jordan Boyd-Graber

Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as "Darmok and Jalad at Tanagra" instead of "We should work together." T…

Language ModelingLanguage ModellingLarge Language ModelMachine Translation+1

Examining Large Pre-Trained Language Models for Machine Translation: What You Don't Know About It

2022-09-15 · Lifeng Han, Gleb Erofeev, Irina Sorokina, Serge Gladkoff 외

Pre-trained language models (PLMs) often take advantage of the monolingual and multilingual dataset that is freely available online to acquire general or mixed domain knowledge before deployment into specific tasks. Extr…

Machine Translation