Tagged articles
NLU
18 articles · Page 1 of 1
This article details a production-ready three-stage pipeline for handling fragment queries in NLU systems: a lightweight rule-based filter routes complete queries directly to JointBERT while sending ambiguous fragments to a small private LLM for semantic completion, then JointBERT performs joint intent classification and slot filling with structured output for downstream services.
JointBERTLLM semantic completionNLU
0 likes · 38 min read

This article explains the technical distinction between intelligent speech— a toolbox of ASR, TTS, NLU, and NLG technologies— and Voice Agent, an end‑to‑end conversational system built on those tools and large‑model reasoning, illustrating their layered relationship, functional gaps, and typical use cases.
ASRDialogue SystemsNLU
0 likes · 7 min read

This article shares reusable AI development techniques for intent detection and slot filling, comparing four solution tiers—from simple prompt engineering to advanced RAG‑enhanced architectures—complete with practical code snippets, performance trade‑offs, and guidance on selecting the optimal approach for reliable conversational agents.
NLUPrompt engineeringRAG
0 likes · 27 min read

GLM introduces a unified pretraining framework that combines autoregressive blank‑filling with 2D positional encoding and span‑shuffle, achieving superior performance over BERT, T5 and GPT on a range of NLU and generation tasks such as SuperGLUE, text‑filling, and language modeling.
2D positional encodingGLMLanguage Model
0 likes · 27 min read

GLM introduces a universal language model that combines autoregressive blank‑filling with 2D positional encoding and span‑shuffle training, achieving superior performance over BERT, T5, and GPT across NLU, conditional and unconditional generation tasks, as demonstrated on SuperGLUE and other benchmarks.
Language ModelNLUPretraining
0 likes · 29 min read

This article reviews the historical development of dialogue management—from early rule‑based and finite‑state approaches to modern data‑driven and reinforcement‑learning methods—and examines how major industry platforms such as Amazon Alexa, Amazon Lex, and RASA implement these techniques in practice.
Amazon Alexa+NLURASA
0 likes · 16 min read

This article explains the architecture of outbound call robots, classifies dialogue system types, details pipeline and end‑to‑end task‑oriented designs, highlights technical challenges such as dialects and transcription errors, and presents optimization techniques like ASR correction and script improvement.
ASR correctionNLUai-optimization
0 likes · 12 min read

This article presents OPPO's XiaoBu Assistant platform, detailing its low‑code workflow for business domain modeling, multi‑type NLU (model‑based, retrieval‑based, and QA), componentized core services, large‑scale text processing, vector retrieval, and flexible dialogue management that together enable a complete skill lifecycle from development to online optimization.
AINLUconversation management
0 likes · 18 min read

The article reviews the importance of query intent recognition in vertical search, outlines its definition, highlights practical challenges such as ambiguous input, multi‑intent queries, timeliness and cold‑start issues, and surveys common rule‑based, statistical, and machine‑learning solutions together with real‑world case studies.
NLUcategory classificationentity recognition
0 likes · 17 min read

This article explains the concept of full‑duplex natural dialogue for Alibaba’s Tmall Genie, illustrates interaction scenarios, and details the technical solution covering device‑side management, speech recognition, language understanding, synthesis, dialogue control, duration handling, and conversation flow.
ASRFull-Duplex DialogueHuman-Computer Interaction
0 likes · 8 min read

This article explains the architecture and core technologies of Ctrip’s intelligent travel customer service, covering NLU, dialogue state tracking, policy learning, intent and slot extraction, multi‑round task bots, and the supporting platform for deployment and future multimodal extensions.
AINLUchatbot
0 likes · 12 min read


58 TechOct 16, 2019 · Artificial Intelligence
This article details the architecture and algorithms behind a voice robot's natural language understanding module, covering single‑sentence intent classification with TextCNN, acoustic quality detection using VGGish‑BiLSTM, semantic similarity matching via DSSM and TextCNN‑Transformer, and slot‑filling with IDCNN‑CRF, along with performance results and future directions.
AINLUTextCNN
0 likes · 11 min read


58 TechAug 14, 2019 · Artificial Intelligence
This article presents a comprehensive overview of an intelligent voice robot's dialogue management system, detailing its architecture, natural language understanding components, dialogue manager design, strategy handling, and workflow processes to achieve fluent multi‑turn interactions in telephone scenarios.
AINLUSpeech Recognition
0 likes · 14 min read

This article explores the architecture and components of Alibaba's Tmall Genie dialogue engine, detailing its bot, skill, domain, intent, entity concepts, NLU strategies—including deep‑learning and fuzzy approaches—skill execution methods, multi‑turn handling, screen‑based interactions, public intents, and the evolution of the platform.
Dialogue EngineNLUmulti-turn conversation
0 likes · 20 min read

This article introduces the "Kelu Fang" product, which leverages knowledge graph, NLU, and ranking technologies to enhance real‑estate search by adding commute‑based filtering and a local view of surrounding facilities, and discusses its architecture, implementation details, and future improvement directions.
AINLUknowledge graph
0 likes · 11 min read

This article introduces the architecture of smart speaker voice interaction systems, covering wake‑word activation, automatic speech recognition (ASR), natural language understanding (NLU), skill processing, text‑to‑speech synthesis (TTS), and the key performance and testing metrics for each component.
ASRNLUTTS
0 likes · 11 min read

Meituan built a custom deep‑learning platform that combines data‑parallel and hybrid parallelism across multi‑GPU/cluster hardware, uses coarse‑grained scheduling and Kaldi‑derived acoustic algorithms, and supports fast NLU model hot‑updates, achieving near‑linear GPU scaling and 6–7× speedups over traditional solutions.
AI infrastructureNLUacoustic modeling
0 likes · 13 min read

The article details the design and implementation of Xiaomi's music‑focused natural language understanding platform, covering its service architecture, intent extraction, knowledge‑base search, slot filling, personalization, and the specific data and modeling challenges encountered.
ASRMusicNLU
0 likes · 9 min read
