Tagged articles
BLEU
11 articles · Page 1 of 1
This article walks through practical large‑model evaluation using the EvalScope platform, covering dataset‑based testing, multi‑dataset aggregation, custom data creation, the BLEU and ROUGE metrics, and how to employ a judge LLM for automated, quantifiable scoring.
BLEUEvalScopeModel Evaluation
0 likes · 26 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.
BLEULLMReinforcement Learning
0 likes · 13 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


Code DAODec 7, 2021 · Artificial Intelligence
This article surveys deep‑learning image captioning, detailing the image encoder, sequence decoder, attention mechanisms and multimodal designs, comparing encoder‑decoder, detection‑backbone, transformer and dense captioning architectures, and explaining generation strategies and BLEU evaluation.
AttentionBLEUCNN
0 likes · 9 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

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


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


Didi TechAug 23, 2020 · Artificial Intelligence
DiDi AI Labs’ NLP team earned third place in the WMT2020 Chinese‑to‑English news translation task with a 36.6 BLEU score, using an enhanced Transformer‑2 model that incorporates self‑attention, relative positional attention, iterative back‑translation, knowledge distillation, data cleaning, ensembling, and other techniques, now deployed across DiDi’s international services.
BLEUDiDi AI LabsNLP
0 likes · 5 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


58 TechMar 13, 2019 · Artificial Intelligence
The article describes the design, workflow, and two‑stage model improvements of 58.com’s intelligent writing robot, which uses template matching, seq2seq with attention and BeamSearch, and slot‑replacement techniques to automatically generate titles and body content for real‑estate and used‑car promotions, achieving high publishing volume and readership.
AI writingBLEUBeamSearch
0 likes · 9 min read
