Tagged articles
machine translation
48 articles · Page 1 of 1
Researchers from City University of Hong Kong, Shenzhen University, USTC, and Oxford propose Seq-Drifting, a context-dependent drifting field method enabling one-step text generation for diffusion language models, achieving 11.2x speedup over 4-step baselines with Gen-PPL of 36.01 on 128-token generation, and validated on translation, summarization, and reasoning tasks.
Seq-Driftingcontext-dependent drifting fielddiffusion language models
0 likes · 11 min read

The authors introduce CULTURE‑MT, the first Chinese‑English social‑media translation benchmark that evaluates cultural effectiveness, define a new metric, release the JUDGER automatic evaluator (86 % accuracy, κ = 0.72), and show that even top models like Gemini 3 pro achieve only 38 % perfect cultural translations.
AI translationDatasetbenchmark
0 likes · 10 min read

This article explains how deep learning models such as RNN, LSTM, GRU and Transformer enable NLP tasks like machine translation, text classification, question answering and text generation, outlines their advantages over traditional methods, and provides a Keras code example for text classification.
KerasNLPPython
0 likes · 8 min read

This article provides a comprehensive overview of Natural Language Processing, detailing the two main branches—Natural Language Understanding and Generation—along with their sub-modules, typical tasks, implementation approaches, a step‑by‑step NLG pipeline, and a three‑layer analysis framework covering lexical, syntactic, and semantic processing.
NLPNatural Language GenerationNatural Language Understanding
0 likes · 9 min read

This article traces the evolution of attention mechanisms from their inaugural application in computer vision and machine translation to their central role in modern Transformer models, detailing the underlying RNN‑Attention designs, the breakthrough in sequence alignment, and the innovations that enabled high‑performance, parallelizable deep learning architectures.
Attention MechanismComputer VisionTransformer
0 likes · 14 min read

The article explains how Tencent's open‑source HY‑MT1.5 tackles the high‑cost, large‑parameter barrier of neural machine translation by offering a 1.8 B‑parameter model that runs on roughly 1 GB of RAM, processes 50 tokens in 0.18 s, supports 33 languages, and uses on‑policy distillation to retain top‑tier accuracy, while providing a step‑by‑step online demo and free compute credits for new users.
HY-MT1.5On-Policy DistillationTencent
0 likes · 5 min read

RIVAL (Reinforcement Learning with Iterative and Adversarial Optimization) introduces an adversarial game between a reward model and a translation LLM, combining qualitative preference rewards with quantitative metrics like BLEU, to overcome distribution shift in RLHF and achieve superior performance on conversational subtitle and WMT translation tasks.
BLEULLMReward Modeling
0 likes · 13 min read

This practical guide walks through the full Transformer architecture for Chinese‑to‑English translation, detailing encoder‑decoder structure, tokenization and embeddings, batch handling with padding and masks, positional encodings, parallel teacher‑forcing, self‑ and multi‑head attention, and the complete forward and back‑propagation training steps.
Positional EncodingPyTorchSelf-Attention
0 likes · 26 min read

The paper proposes a bidirectional optimization framework that fine‑tunes the low‑resource NLLB‑200 translation model with LoRA using data generated by ChatGPT, while also translating low‑resource prompts with NLLB before feeding them to LLMs, thereby improving multilingual translation quality yet requiring careful validation of noisy synthetic data.
LLMLoRANLLB
0 likes · 28 min read

This article provides a comprehensive guide on developing a Python tool to convert English videos into versions with Chinese dubbing and subtitles, covering all steps from audio extraction to final synthesis.
AI toolsFFmpegPython
0 likes · 5 min read

The article introduces Marco‑o1, an open‑source LLM that enhances complex reasoning by fine‑tuning on Chain‑of‑Thought data, integrating Monte‑Carlo Tree Search, introducing mini‑step actions and a reflection mechanism, and evaluates its performance on multilingual math and translation benchmarks.
LLMMonte Carlo Tree Searchartificial intelligence
0 likes · 15 min read

This article walks through the complete process of fine‑tuning both domain‑specific and large‑language translation models on Kubernetes documentation, covering data preparation, model selection, training configurations, the differences between Seq2Seq and CausalLM, and how LoRA can dramatically reduce resource usage while improving performance.
AILLMLoRA
0 likes · 7 min read

Paperpolisher is an AI-powered tool using Baidu's ERNIE large model and Comate to translate and polish Chinese academic papers into high-quality English, leveraging large paper datasets and retrieval augmentation, streamlining code generation and improving acceptance chances for submissions to top conferences.
AI coding assistantBaidu ComateERNIE large model
0 likes · 9 min read

This article provides a comprehensive, beginner-friendly explanation of the Transformer architecture, covering its encoder‑decoder structure, self‑attention, multi‑head attention, positional encoding, residual connections, decoding process, final linear and softmax layers, and training considerations, illustrated with numerous diagrams and code snippets.
Self-AttentionTransformerdeep learning
0 likes · 24 min read

This presentation details the concepts, methodologies, and experimental results of instruction fine‑tuning for Huawei's Pangu large language model, covering model scale, architecture, training strategies, data quality, parallelism techniques, and case studies on Chinese‑English translation and Thai language adaptation.
Efficient Fine-Tuninginstruction fine-tuningmachine translation
0 likes · 19 min read

This article reviews the technical background of simultaneous speech translation, compares offline and real‑time scenarios, details ASR and MT technologies, describes the system architecture and design strategies, and discusses the major challenges and solutions for deploying robust, low‑latency translation services.
ASRHuaweiReal-time
0 likes · 16 min read


21CTOApr 27, 2023 · Artificial Intelligence
This article explains the Transformer model—from its encoder‑decoder structure and self‑attention mechanism to multi‑head attention, positional encoding, residual connections, training loss, and inference strategies—providing a clear, visual walkthrough for readers new to modern NLP architectures.
Self-AttentionTransformerdeep learning
0 likes · 21 min read

This article investigates the translation quality of Deepl and ChatGPT for the game 'Naraka: Bladepoint' by comparing their outputs against professional human translations across Chinese‑English, Chinese‑Spanish, and English‑Spanish pairs using BLEU scores and manual assessment, revealing strengths and limitations of each system.
AIGCBLEUChatGPT
0 likes · 12 min read

This article traces the historical convergence of mathematics and linguistics, from 19th‑century pioneers to post‑war computer‑driven research, highlighting how statistical, probabilistic, and formal methods laid the foundation for machine translation, morphological analysis, and contemporary natural language processing.
history of linguisticsmachine translationmathematical linguistics
0 likes · 7 min read

This article reviews the integration of contrastive learning into text generation, explains why it helps mitigate exposure bias, introduces the CoNT framework with three key improvements, presents extensive experiments on translation, summarization, code comment and data‑to‑text tasks, and discusses practical deployment considerations.
AICoNTContrastive Learning
0 likes · 21 min read

This article reviews the IWSLT 2022 competition tasks, explains Huawei’s cascade offline speech‑to‑text translation pipeline, details four major technical innovations—including ensemble‑based ASR de‑noise, context‑aware re‑ranking, domain‑controlled training, and length‑control strategies—and presents experimental results that demonstrate Huawei’s leading performance across multiple language directions.
ASRHuaweiIWSLT
0 likes · 18 min read


21CTOJul 9, 2022 · Artificial Intelligence
Meta has open‑sourced its new NLLB‑200 model, a single AI system that translates 200 languages with up to 44 % higher quality than its predecessor, supporting numerous low‑resource languages and powering billions of daily translations across Facebook and Instagram to improve user experience and content safety.
MetaNLLB-200machine translation
0 likes · 3 min read

DeltaLM is a new multilingual pretrained encoder‑decoder model that leverages a pretrained encoder and a novel decoder to improve multilingual neural machine translation, offering efficient training, strong cross‑language transfer, zero‑shot translation, and superior performance on various translation and summarization tasks.
DeltaLMNMTmachine translation
0 likes · 13 min read

This article reviews recent advances in speech translation, discusses ByteDance's practical deployments, compares cascade and end‑to‑end modeling approaches, introduces improved encoder‑decoder architectures and training strategies, and reports state‑of‑the‑art results on the IWSLT 2021 benchmark.
AIByteDanceEnd-to-End
0 likes · 15 min read

This article presents a comprehensive guide to deploying machine translation at Vivo, covering business analysis, algorithm choices beyond standard NMT, language detection challenges, data collection and cleaning, scientific evaluation methods, and engineering optimizations to deliver a seamless user experience.
AINMTengineering
0 likes · 20 min read

The ByteDance Engine Developer Community Meetup featured senior engineers from ByteDance and OPPO who presented the latest advances in intelligent audio signal processing, natural language processing for recommendation, entity linking in knowledge graphs, and multimedia machine translation, highlighting practical applications and performance challenges.
artificial intelligenceknowledge graphmachine translation
0 likes · 4 min read

Tencent’s machine‑translation teams clinched five first‑place wins in the WMT2021 news track—covering Chinese‑English, Japanese‑English and English‑German limited‑resource tasks—outperforming 82 competing teams and showcasing the impact of its AI‑driven translation engine across its products.
AI competitionBLEUTencent
0 likes · 4 min read

iQIYI’s multi‑language subtitle machine‑translation system combines a one‑to‑many transformer, context‑fusion encoding, four custom attention masks, masked language modeling, global decoding loss, reconstruction and error‑correction modules, plus pronoun, idiom and name‑handling tricks, achieving higher quality than third‑party services and even surpassing human translation for several languages.
One-to-Many ModelSubtitle Translationerror correction
0 likes · 17 min read

This article presents Bytedance's industrial machine‑translation platform, describing its global deployment, diverse product demos, underlying sequence‑to‑sequence models, BERT‑enhanced training strategies, prune‑tune sparsity techniques, multilingual pre‑training, document translation, and a high‑performance inference engine.
BERTPretrainingmachine translation
0 likes · 19 min read

This article surveys recent multimodal AI research, covering video scene‑aware dialog with a GPT‑2 based unified pre‑training framework, dual‑channel multi‑hop reasoning for visual dialog, capsule‑network‑enhanced multimodal machine translation, and graph‑neural‑network‑driven multimodal translation, highlighting experimental results and future directions.
Graph Neural Networkmachine translationmultimodal AI
0 likes · 12 min read

This article explains key concepts of neural machine translation, covering Seq2Seq encoder‑decoder models, beam search strategies, BLEU evaluation, various attention mechanisms, and the enhancements introduced in Google's Neural Machine Translation system to improve speed, OOV handling, and translation quality.
AttentionBLEUGNMT
0 likes · 11 min read

This article presents a comprehensive overview of Didi's machine translation platform, covering its evolution from statistical to neural models, the Transformer architecture with relative position and larger FFN, data preparation, training strategies such as back‑translation and knowledge distillation, deployment optimizations with TensorRT, and the team's successful participation in the WMT2020 news translation task.
BLEUTensorRTback-translation
0 likes · 14 min read

This article presents a comprehensive overview of Ctrip's multilingual machine translation platform, detailing demand analysis, system architecture, data pipeline, algorithmic innovations such as task‑space fusion and term‑translation interventions, as well as extensive performance optimizations for low‑resource languages.
AICtripdata pipeline
0 likes · 20 min read


Didi TechOct 27, 2020 · Artificial Intelligence
Didi's machine translation system combines a Transformer‑big architecture with relative position representations, enlarged feed‑forward networks, iterative back‑translation, knowledge‑distillation and domain fine‑tuning, optimized via TensorRT for speed, achieving a BLEU 36.6 and third place in the WMT2020 Chinese‑to‑English news task.
BLEUTensorRTTransformer
0 likes · 15 min read

This article reviews how large‑scale pretrained language models have reshaped NLP, outlines the challenges of applying them to machine translation, introduces the APT framework and the GRET architecture for better encoder‑decoder integration, and reports experimental gains and future research directions.
AIAPT frameworkGRET
0 likes · 10 min read


21CTOApr 20, 2020 · Artificial Intelligence
This article examines DeepL’s translation system, comparing its neural‑network‑driven output to Google and other services, detailing its Icelandic HPC infrastructure, data collection, architectural choices, language support, strengths, limitations, and expert opinions on why it often delivers more natural translations.
AIHPCcomparison
0 likes · 9 min read

This article reviews recent research on machine translation that tackles the training‑inference distribution gap, exposure bias, and slow autoregressive decoding by introducing scheduled sampling, differentiable sequence‑level losses, cube‑pruning, and sequence‑aware non‑autoregressive decoding, showing BLEU gains and significant speedups.
BLEUExposure biasNLP
0 likes · 16 min read

This article systematically reviews the history, core concepts, variants, and practical implementations of attention mechanisms—from early additive and multiplicative forms to self‑attention, multi‑head attention, and recent transformer‑based models—highlighting why attention has become fundamental in modern AI research.
AttentionNLPSelf-Attention
0 likes · 16 min read

This article introduces Grammatical Error Correction (GEC), explains its main error categories, outlines four key challenges, reviews evaluation metrics and the evolution of NLP approaches, and showcases practical solutions and product applications developed by Liulishuo.
Grammatical Error CorrectionNLPdeep learning
0 likes · 11 min read

This article surveys the evolution of machine translation from early rule‑based systems to modern neural architectures, explains how translation engines are trained, highlights recent advances such as attention and Transformers, and shares practical experience and current challenges in the field.
Attention MechanismTransformerartificial intelligence
0 likes · 11 min read


ITPUBMar 6, 2019 · Artificial Intelligence
A recent WeChat translation bug that turned a name into bizarre Chinese phrases sparked a deep dive into neural machine translation, exposing algorithmic shortcomings, training‑data biases, and the broader uncertainties that affect modern AI‑driven translators.
AINMTmachine translation
0 likes · 10 min read

This article presents a comprehensive overview of Baidu's Chinese text correction technology, covering its background, error types, system architecture, key detection, candidate recall and ranking methods, core language and knowledge techniques, and real-world applications in open-domain and scenario-specific contexts.
Baidumachine translationtext correction
0 likes · 13 min read

This article reviews the current state of machine translation, explores the challenges of ambiguity, quality, and domain specificity, and presents human‑in‑the‑loop translation techniques—including attention‑enhanced models, transformer architectures, and online learning—while discussing practical productization and deployment considerations.
AI productizationAttentionTransformer
0 likes · 16 min read

This article traces the history of machine translation—from early rule‑based systems through statistical models that leveraged parallel corpora, to modern neural network approaches—while highlighting current applications, challenges, and future directions in the field.
AI applicationsmachine translationnatural language processing
0 likes · 9 min read


AntTechAug 1, 2018 · Artificial Intelligence
An extensive overview of ACL 2018, featuring acceptance statistics, award-winning papers, tutorial insights, and concise summaries of notable research across machine translation, semantic parsing, question answering, domain adaptation, text classification, summarization, dialogue systems, generation, and related tools.
ACL 2018Dialogue SystemsNLP
0 likes · 12 min read

This article explains why attention mechanisms were introduced into Seq2Seq models, how they address the limitations of fixed‑length encoding, the role of bidirectional RNNs, and showcases their impact on machine translation and image captioning with illustrative diagrams.
Attention MechanismRNNSeq2Seq
0 likes · 10 min read

The article reviews ACL 2016’s tutorial program, summarizing key talks on computer‑aided translation, neural machine translation, semantic sense representation, short‑text understanding, and highlights selected papers on multimodal translation, coverage modeling, and language‑vision grounding, illustrating deep learning’s impact on NLP research.
ACL 2016NLPdeep learning
0 likes · 13 min read

This NSF‑funded project aims to develop algorithms that incrementally process partially observed data, integrating generative models with reinforcement‑learning policies to decide when to act, applied to simultaneous machine translation and quiz‑bowl style question answering.
Bayesian inferenceGenerative ModelsQuestion Answering
0 likes · 4 min read
