0 views collected around this technical thread.
This article explains why ECC memory modules use an extra chip, how bit‑flip errors occur in 64‑bit CPU‑memory transfers, and how simple parity and Hamming‑code algorithms detect and correct single‑bit errors while only detecting double‑bit errors, illustrating the principles with diagrams and examples.
This article describes Laiye's OCR error‑correction system, detailing the background challenges of Chinese character recognition, the analysis of three possible solutions, the chosen post‑processing approach, model architecture, training data, loss design, online inference, and experimental results showing a measurable performance boost.
This article provides an in‑depth overview of QR codes, covering their definition, types, structural features, versioning, error‑correction levels, encoding and decoding processes, commercial uses, design considerations, and practical Python examples for generating and reading QR codes.
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.
This article explains the concept of forward error correction (FEC), its role in transport‑layer protocols, illustrates basic Hamming‑code design, discusses advanced techniques such as fountain codes, and outlines best practices for applying FEC to improve reliability and efficiency in network communications.
This article presents a comprehensive study on slot (entity) recognition and error correction for voice robots, describing the labeling scheme, data annotation, IDCNN+CRF and BiLSTM+CRF models, a pinyin‑based similarity algorithm, and reporting significant accuracy improvements in real‑world deployments.
This article details how Ctrip's hotel search system was optimized through storage compression, spatial indexing, KV storage, semantic query generation, context‑aware error correction, and a custom domain‑specific language, balancing performance, flexibility, and user experience for large‑scale online travel services.
This article describes how Xiaomi's AI team tackles Automatic Speech Recognition (ASR) query errors by analyzing error patterns, employing BERT, ELECTRA and a soft‑masked BERT model, generating synthetic noisy data with a fuzzy‑phoneme generator, and presenting experimental results and future research directions.
This article presents a comprehensive overview of automatic speech recognition (ASR) error correction techniques employed by Xiaomi's Xiao‑Ai team, detailing problem definition, related work on BERT and ELECTRA, a custom generator‑discriminator architecture with a fuzzy‑phoneme simulator, experimental results, and prospective research directions.
Recent advances in map‑search text processing replace rule‑based pipelines with machine‑learning and deep‑learning models for query analysis, error correction, rewriting, and omission, using phonetic and spatial entity correction, vector‑based similarity, and CRF sequence labeling within a three‑stage architecture of analysis, recall, and ranking to deliver more precise POI results.