BestHub
Sign in
Tagged articles
9 articles
Page 1 of 1
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Jan 31, 2026 · Artificial Intelligence

How Engram Lets Large Models Swap GPU Memory for Cheap RAM to ‘Look Up’ Knowledge

The article dissects DeepSeek’s new Engram architecture, which separates computation from memory by using a large, cheap‑RAM‑based lookup table to store factual knowledge, allowing the transformer’s compute layers to focus on reasoning, dramatically reducing GPU memory demand while improving code, math, and long‑context performance.

EngramGPU MemoryMemory-Compute Architecture
0 likes · 7 min read
How Engram Lets Large Models Swap GPU Memory for Cheap RAM to ‘Look Up’ Knowledge
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Nov 7, 2025 · Backend Development

How to Achieve MySQL‑LIKE Style Fuzzy Search in Elasticsearch 8.x

This article walks through the challenge of implementing MySQL‑LIKE style front‑and‑back wildcard searches in Elasticsearch, comparing match, match_phrase, n‑gram, legacy wildcard queries, and the new wildcard field type introduced in ES 7.9+, with code samples, performance benchmarks, and practical recommendations for choosing the optimal solution.

ElasticsearchN-gramfuzzy-search
0 likes · 10 min read
How to Achieve MySQL‑LIKE Style Fuzzy Search in Elasticsearch 8.x
JavaEdge
JavaEdge
Mar 15, 2025 · Artificial Intelligence

Boost NLP Model Performance with n-gram Feature Engineering

This article explains why feature engineering is crucial for NLP tasks, introduces n‑gram enhancements, provides Python implementations for generating bi‑gram and higher‑order features, demonstrates dynamic padding for text length standardization, and offers practical deployment tips such as feature dimension control and monitoring.

Deep LearningN-gramNLP
0 likes · 7 min read
Boost NLP Model Performance with n-gram Feature Engineering
DataFunSummit
DataFunSummit
Dec 23, 2021 · Artificial Intelligence

User Clustering Techniques in Tencent KanDian: From Traditional Algorithms to N‑gram and action2vec

This article explains how Tencent KanDian analyzes user behavior by introducing the product, describing common clustering scenarios, reviewing traditional unsupervised methods, and detailing advanced path‑based approaches such as N‑gram and action2vec, while discussing their advantages, limitations, and practical applications.

N-gramTencentaction2vec
0 likes · 12 min read
User Clustering Techniques in Tencent KanDian: From Traditional Algorithms to N‑gram and action2vec
DataFunTalk
DataFunTalk
Nov 8, 2021 · Artificial Intelligence

User Behavior Clustering in Tencent Kankan: From Traditional Unsupervised Methods to N‑gram and action2vec

This article introduces Tencent Kankan's product landscape and explores various user clustering techniques—including classic unsupervised algorithms, N‑gram based sequence clustering, and deep‑learning driven action2vec—detailing their implementation steps, advantages, limitations, and practical insights for product optimization.

N-gramTencentaction2vec
0 likes · 12 min read
User Behavior Clustering in Tencent Kankan: From Traditional Unsupervised Methods to N‑gram and action2vec
Tongcheng Travel Technology Center
Tongcheng Travel Technology Center
Nov 1, 2019 · Artificial Intelligence

Improving International Hotel Room‑Type Merging with Text Similarity and Machine‑Learning Models

This article describes how a large‑scale international hotel platform reduced room‑type merging errors and user complaints by applying rule‑based methods, text‑similarity algorithms (Jaccard, LCS, N‑Gram) and supervised machine‑learning classifiers such as fastText to standardize and merge heterogeneous room‑type data.

N-gramfastTexthotel
0 likes · 9 min read
Improving International Hotel Room‑Type Merging with Text Similarity and Machine‑Learning Models
WeChat Backend Team
WeChat Backend Team
Sep 3, 2019 · Artificial Intelligence

How Tencent Scaled Massive n‑gram Language Models for Real‑Time Speech Recognition

This article presents a distributed system that efficiently supports large‑scale n‑gram language models for automatic speech recognition by introducing caching, a two‑level distributed index, batch processing, and a cascading fault‑tolerance mechanism, demonstrating robust scalability and low communication overhead in Tencent's WeChat ASR service.

Language ModelN-gramcaching
0 likes · 35 min read
How Tencent Scaled Massive n‑gram Language Models for Real‑Time Speech Recognition