← Explore

Machine Translation

cs.CL · 7 papers

Featured
cs.CL · 2017

Attention Is All You Need — Explaining the Transformer

BLEU: 28.4

Ashish Vaswani, Noam Shazeer +6

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also…

Code· 17k
cs.CL · 2024

Gemini 1.5: Unlocking Multimodal Long-Context

Synthetic Text Haystack: >99.7%

Gemini Team, Petko Georgiev +1135

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning…

cs.CL · 2021

RoFormer: Enhanced Transformer with Rotary Position Embedding

BLEU: 27.5

Jianlin Su, Yu Lu +4

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of…

Code· 1.1k
cs.LG · 2021

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

pre-training speedup: 7x

William Fedus, Barret Zoph, Noam Shazeer

In deep learning, models typically reuse the same parameters for all inputs. Mixture of Experts (MoE) defies this and instead selects different parameters for each incoming…

Code· 3.0k
cs.LG · 2019

Exploring the Limits of Transfer Learning with T5

GLUE: 90.3

Colin Raffel, Noam Shazeer +7

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language…

Code· 6.5k
cs.CL · 2014

Sequence to Sequence Learning with Neural Networks

BLEU: 34.81

Ilya Sutskever, Oriol Vinyals, Quoc V. Le

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets…

cs.CL · 2013

Word2Vec Demystified: Efficient Estimation of Word Representations in Vector Space

Semantic Accuracy: 55%

Tomas Mikolov, Kai Chen +2

We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a…

Code· 1.6k