Continuous Semantic Enhancement for Neural Machine Translation: Methodology, Experiments, and Community Deployment

This article introduces a continuous semantic enhancement approach for neural machine translation that overcomes the limitations of discrete data‑augmentation techniques, details the neighbor risk minimization training objective, presents benchmark improvements on ACL‑2022 datasets, and describes practical deployment and fine‑tuning workflows in the Modu community.

Neural Machine Translationcontinuous semantic augmentationcontrastive learning

0 likes · 19 min read

Continuous Semantic Enhancement for Neural Machine Translation: Methodology, Experiments, and Community Deployment

DataFunSummit

Jan 13, 2022 · Artificial Intelligence

DeltaLM: A Multilingual Pretrained Encoder‑Decoder Model for Neural Machine Translation

DeltaLM is a multilingual pretrained encoder‑decoder model that leverages cross‑lingual transfer from a pretrained encoder and novel decoder architecture, employs span‑corruption and translation‑pair pretraining tasks, and uses a two‑stage fine‑tuning strategy to achieve strong zero‑shot and supervised translation performance across over 100 languages.

Cross-Lingual TransferDeltaLMNeural Machine Translation

0 likes · 12 min read

DeltaLM: A Multilingual Pretrained Encoder‑Decoder Model for Neural Machine Translation

DataFunTalk

Apr 7, 2021 · Artificial Intelligence

Alibaba's Advances in Multilingual Neural Machine Translation: Research and Practice

This article presents Alibaba's comprehensive research on multilingual neural machine translation, covering motivations, model architectures, intermediate language modules, data‑augmentation strategies such as repair translation, integration of pre‑trained models with adapters, and engineering optimizations that enable a production‑ready system supporting over 200 languages.

AdapterAlibabaNeural Machine Translation

0 likes · 21 min read

Alibaba's Advances in Multilingual Neural Machine Translation: Research and Practice

Sohu Tech Products

Nov 18, 2020 · Artificial Intelligence

Understanding Sequence‑to‑Sequence (seq2seq) Models and Attention Mechanisms

This article explains the fundamentals of seq2seq neural machine translation models, covering encoder‑decoder architecture, word embeddings, context vectors, RNN processing, and the attention mechanism introduced by Bahdanau and Luong, with visual illustrations and reference links for deeper study.

Deep LearningEmbeddingNeural Machine Translation

0 likes · 11 min read

Understanding Sequence‑to‑Sequence (seq2seq) Models and Attention Mechanisms

Sohu Tech Products

Jan 9, 2019 · Artificial Intelligence

Understanding the Transformer Model: Attention, Self‑Attention, and Multi‑Head Mechanisms

This article provides a comprehensive, step‑by‑step explanation of the Transformer architecture, covering its encoder‑decoder structure, self‑attention, multi‑head attention, positional encoding, residual connections, and training processes, illustrated with diagrams and code snippets to aid readers new to neural machine translation.

Deep LearningNeural Machine TranslationPositional Encoding

0 likes · 16 min read

Understanding the Transformer Model: Attention, Self‑Attention, and Multi‑Head Mechanisms

Alibaba Cloud Developer

May 11, 2018 · Artificial Intelligence

How Suffix Prediction Boosts English‑Russian Neural Machine Translation Accuracy

Researchers introduce a novel suffix‑prediction mechanism for neural machine translation that separately generates stems and suffixes during decoding, dramatically reducing out‑of‑vocabulary errors and morphological mistakes in English‑Russian translation, achieving consistent improvements across RNN and Transformer models on large‑scale news and e‑commerce datasets.

English-RussianMorphologically Rich LanguagesNeural Machine Translation

0 likes · 10 min read

How Suffix Prediction Boosts English‑Russian Neural Machine Translation Accuracy

Alibaba Cloud Developer

Jun 5, 2017 · Artificial Intelligence

Alibaba’s Distributed Training Boosts Neural Machine Translation Speed

Since its 2013 debut, Neural Machine Translation (NMT) has approached human quality, but training costs are high; Alibaba’s team developed a distributed NMT system in 2017, employing data‑parallel, model‑average, BMUF, Downpour SGD, and Ring‑allReduce techniques to cut training time from over 20 days to a few days while maintaining translation quality.

BMUFDistributed TrainingDownpour SGD

0 likes · 18 min read

Alibaba’s Distributed Training Boosts Neural Machine Translation Speed