semantic retrieval

Zhihu Tech Column

Oct 10, 2024 · Artificial Intelligence

Massive Multi-Label Text Classification via Semantic Retrieval and Large AI Model

This article presents a method for massive multi-label text classification on Zhihu content by combining a semantic retrieval model with a proprietary large AI model, detailing the challenges of large label spaces, model architecture, loss optimization, and experimental results showing significant accuracy gains.

BGEZhihularge language model

0 likes · 16 min read

Massive Multi-Label Text Classification via Semantic Retrieval and Large AI Model

iQIYI Technical Product Team

Sep 26, 2024 · Artificial Intelligence

AI-Powered Search in iQIYI: Techniques, Architecture, and Implementation

iQIYI’s AI‑powered search expands beyond title‑only queries by handling fuzzy role, plot, star, award, and semantic searches, using Chain‑of‑Thought‑generated TIPS, Retrieval‑Augmented Generation with sophisticated indexing, chunking, embedding, reranking, and prompt‑engineering to deliver personalized, accurate video recommendations that boost user engagement.

AI SearchChain-of-ThoughtEmbedding

0 likes · 15 min read

AI-Powered Search in iQIYI: Techniques, Architecture, and Implementation

Xiaohongshu Tech REDtech

Aug 1, 2024 · Artificial Intelligence

Xiaohongshu Search Advertising Recall: Practices, Metrics, and Large‑Model Integration

Xiaohongshu’s search advertising recall system evolves from keyword bidding to BERT‑based vector retrieval and LLM‑enhanced query rewriting, using dual semantic and efficiency models, water‑level metrics, and GPU‑accelerated engineering to achieve 80 % click coverage, 60 % conversion coverage and a 5 % CPM lift.

Search Advertisingartificial intelligenceefficiency optimization

0 likes · 33 min read

Xiaohongshu Search Advertising Recall: Practices, Metrics, and Large‑Model Integration

Baidu Tech Salon

Nov 10, 2023 · Artificial Intelligence

Baidu Search Deep Learning Model Architecture and Optimization Practices

Baidu's Search Architecture team details how its deep‑learning models have evolved to deliver direct answer results via semantic embeddings, describes a massive online inference pipeline that rewrites queries, ranks relevance, and classifies types, and outlines optimization techniques—including data I/O, CPU/GPU balancing, pruning, quantization, and distillation—to achieve high‑throughput, low‑latency search.

BaiduGPU optimizationInference System

0 likes · 13 min read

Baidu Search Deep Learning Model Architecture and Optimization Practices

Baidu Geek Talk

Nov 9, 2023 · Artificial Intelligence

Deep Learning Model Architecture Evolution in Baidu Search

The article chronicles Baidu Search’s Model Architecture Group’s evolution of deep‑learning‑driven search, detailing the shift from inverted‑index to semantic vector indexing, the use of transformer‑based models for text and image queries, large‑scale offline/online pipelines, and extensive GPU‑centric optimizations such as pruning, quantization and distillation, all aimed at delivering precise, cost‑effective results to hundreds of millions of users.

ERNIEGPU inferencedeep learning

0 likes · 14 min read

Deep Learning Model Architecture Evolution in Baidu Search

Baidu Geek Talk

Mar 23, 2023 · Artificial Intelligence

Advanced Image Search in Baidu Netdisk: Semantic Vector Retrieval and Multi-Modal Fusion

Baidu Netdisk’s new image search combines ERNIE‑ViL‑based semantic vectors, cross‑modal matching and metadata such as timestamps, GPS and facial tags, using LSH‑optimized indexing to let users find specific photos among billions with natural‑language queries, delivering faster, more accurate results without manual tagging.

Cloud ComputingERNIE-ViLImage Search

0 likes · 11 min read

Advanced Image Search in Baidu Netdisk: Semantic Vector Retrieval and Multi-Modal Fusion

Baidu Geek Talk

Oct 11, 2021 · Backend Development

Baidu Search Closed-Door Technical Symposium

The Baidu Search Closed‑Door Technical Symposium, the first core technical forum hosted by Baidu’s Search Architecture Department, brings senior engineers and junior backend developers together to discuss semantic retrieval, data‑driven big‑data processing, and vertical search offline architecture, while offering limited‑capacity sessions, networking gifts, and travel subsidies.

Baidu SearchCloud-Native Architecturebackend development

0 likes · 6 min read

Baidu Search Closed-Door Technical Symposium

DataFunTalk

Jul 2, 2021 · Artificial Intelligence

Vector Retrieval for Community Forum Search Using Milvus at Dingxiangyuan

This article describes how Dingxiangyuan's algorithm team adopted Milvus for distributed vector indexing to improve semantic search in their community forum, detailing the background, retrieval workflow, various embedding models—including Bi‑Encoder, Spherical Embedding, and Knowledge Embedding—and summarizing the benefits and future applications.

EmbeddingMilvusNLP

0 likes · 10 min read

Vector Retrieval for Community Forum Search Using Milvus at Dingxiangyuan

DataFunTalk

Jan 15, 2021 · Artificial Intelligence

Zhihu Search Text Relevance Evolution and BERT Knowledge Distillation Practices

This talk by Zhihu search algorithm engineer Shen Zhan details the evolution of text relevance models from TF‑IDF/BM25 to deep semantic matching and BERT, explains the challenges of deploying BERT at scale, and describes practical knowledge‑distillation techniques that improve both online latency and offline storage while maintaining search quality.

BERTMachine LearningSearch Relevance

0 likes · 14 min read

Zhihu Search Text Relevance Evolution and BERT Knowledge Distillation Practices

DataFunTalk

Jan 2, 2020 · Artificial Intelligence

Improving Zhihu Search: Query Understanding, Term Weighting, Synonym Expansion, Query Rewriting, and Semantic Retrieval

This article details Zhihu's search engineering advances over the past year, covering long‑tail query challenges, term‑weight calculation, synonym expansion, query rewriting with translation models and reinforcement learning, and semantic retrieval using BERT‑based embeddings, while outlining future research directions.

NLPSearchquery rewriting

0 likes · 14 min read