The article explains how to transform a pretrained speech model into a product‑ready assistant by defining demonstration data, clarifying team debates on persona, safety, and length, contrasting alignment with pretraining, and highlighting common pitfalls to avoid during deployment.
The article examines two recent open‑source projects, EMPA and MAPO, which introduce process‑level evaluation and long‑horizon reinforcement learning to move large‑model empathy from single‑turn responses toward sustained, measurable multi‑turn support, and discusses their frameworks, benchmarks, and experimental results.
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.
The article introduces CID-GraphRAG, a novel framework that combines intent‑driven graphs with semantic similarity search to improve multi‑turn intelligent customer service, detailing its architecture, dual‑layer retrieval mechanism, evaluation against baseline models, and future research directions.
The article reviews the evolution of large‑model technology, details Kuaishou’s self‑developed “Kuaishou Yi” model architecture, data pipeline, evaluation benchmarks, and explains how the AI XiaoKuai assistant achieves multimodal, personable interactions while also announcing related recruitment opportunities.
This article reviews the evolution of dialogue systems from modular task‑oriented designs to end‑to‑end large‑scale models, detailing Baidu's PLATO series, their technical innovations, real‑world deployments, challenges such as inference efficiency and safety, and future research directions in conversational AI.
This article details the development journey of OPPO's conversational AI assistant XiaoBu, covering its historical background, product features, four years of technical evolution, challenges in skill building and user understanding, anti‑failure strategies, and future directions in multimodal AI assistants.
The DataFun 2022 NLP Summit, held on July 30, brings together top researchers and industry leaders from Alibaba, Baidu, Microsoft, Amazon, and more to present the latest advances in large‑scale pre‑training, multimodal perception, information extraction, dialogue interaction, machine translation, and practical AI deployments, with live streaming and free registration via QR code.
This article explores why AI‑to‑AI dialogue is needed, outlines the overall architecture of an AI conversation system, details text‑generation and voice‑synthesis techniques, and examines how such technology can power immersive metaverse social experiences, illustrated with the XiaoIce Island platform.
This article presents a comprehensive overview of OPPO's XiaoBu Assistant, detailing its research background, chat skill architecture, evolution from retrieval and rule‑based methods to generative models, industry model comparisons, decoding and ranking strategies, safety mechanisms, performance optimizations, and evaluation results.
Meituan’s intelligent customer service platform, serving over 630 million users and 7.7 million merchants, integrates six core AI capabilities—including problem recommendation, understanding, dialogue management, answer supply, response recommendation, and session summarization—across pre‑sale, in‑sale, after‑sale and internal scenarios, leveraging multi‑turn dialogue, intent recognition, knowledge‑graph Q&A, and the Moses platform, while targeting future end‑to‑end and emotionally intelligent interactions.
This article presents Meituan's intelligent customer service practice, covering background, six core AI capabilities such as problem recommendation, understanding, dialogue management, answer supply, script recommendation, and conversation summarization, as well as the Moses dialogue platform and future research directions.
This article presents a comprehensive case study of applying named‑entity‑recognition (NER) techniques to the smart chat assistant of 58.com’s yellow‑page service, covering business background, model selection (BiLSTM‑CRF, IDCNN‑CRF, BERT), data‑augmentation, focal loss, fusion of rule‑based and neural methods, context modeling, online performance, and future research directions.
The article presents a comprehensive overview of Ant Group's intelligent service research, summarizing recent AI‑focused papers on text classification, stance detection, data augmentation, knowledge distillation for ranking, reinforcement‑learning‑based dialogue clarification, behavior‑cloning dialogue systems, anti‑fraud outbound bots, tag‑based service recommendation, and multi‑agent service groups, while also highlighting future directions and recruitment opportunities.
This article introduces the typical applications of intelligent question answering, compares chat‑type, knowledge‑type and task‑type bots, and then details the end‑to‑end architecture, knowledge‑base construction, semantic‑equivalence modeling with BERT‑BIMPM, knowledge‑graph QA pipelines, and NL2SQL techniques, concluding with practical deployment insights.
This article reviews the evolution of pretraining models in NLP, discusses the practical challenges of deploying large models such as inference latency, knowledge integration, and task adaptation, and presents Xiaomi’s optimization techniques including knowledge distillation, low‑precision inference, operator fusion, and multi‑granularity segmentation for dialogue systems.
This article reviews the latest advances in open-domain dialogue systems, covering classification, end‑to‑end generation challenges, knowledge‑controlled generation, automated evaluation, large‑scale latent‑space models such as PLATO, and outlines future research directions for building more coherent and controllable conversational AI.
This presentation by Baidu chief architect Wang Fan reviews the classification of dialogue systems, discusses the challenges of end‑to‑end open‑domain conversation generation, introduces multi‑mapping and knowledge‑grounded techniques, describes large‑scale PLATO models and automated evaluation, and outlines future research directions.
This article explores how analyzing speech acts—such as inquiries, commands, and expressions—within user utterances can reveal semantic focus points that guide robots in inferring appropriate emotional responses, highlighting classification methods, high‑frequency examples, and a configurable formula for emotion generation in AI dialogue systems.
This article presents a comprehensive overview of emotion analysis technologies employed in Alibaba's intelligent customer service platform, detailing models for user emotion detection, emotional response generation, service quality inspection, satisfaction prediction, and intelligent human‑agent handoff, along with experimental results and future research directions.
This article examines how emotion analysis techniques are integrated into intelligent customer‑service systems, detailing architecture, multi‑level semantic models, offline and online comfort frameworks, generative dialogue models, service‑quality inspection, and conversation‑satisfaction prediction, all supported by extensive experiments and real‑world data.
The article summarizes five Ant Financial papers accepted at WWW2020, covering an efficient sentence‑similarity model (Enhanced‑RCNN), a graph‑based multi‑turn dialogue system (IntentDial), a low‑label captcha recognizer, a solver for billion‑scale knapsack problems, and a novel equal‑distance/equal‑distribution triplet loss for image retrieval.
The article presents an in‑depth overview of Microsoft XiaoIce’s conversational AI platform, covering system classification, the three major dialogue directions, long‑term conversation handling, query understanding and rewriting, few‑shot learning with prototypical networks, retrieval and generation models, empathy modeling, and the concept of AI beings for building personalized chatbots.
This presentation reviews recent progress in spoken and multimodal dialogue systems, covering X‑driven architectures, task‑oriented and open‑domain approaches, NLU/DM integration, FAQ, KB/KG‑driven methods, document‑driven dialogue, and outlines remaining challenges and future research directions.
This talk presents how Meituan leverages knowledge‑graph QA (KBQA) across restricted and complex smart‑interaction scenarios, compares semantic‑parsing and information‑retrieval approaches, introduces three‑layer concept nodes to handle entity explosion and non‑connected queries, and outlines architectural refinements for multi‑turn dialogue integration.
This paper introduces Heterogeneous Memory Networks (HMNs), combining context‑free and context‑aware memory modules to jointly process user queries, dialogue history, and knowledge bases, achieving state‑of‑the‑art performance on three task‑oriented dialogue datasets in both BLEU and F1 metrics.
This article reviews recent progress and open research problems in human‑machine dialogue, covering both open‑domain chat and task‑oriented systems, with focus on reply quality, decoding, retrieval‑augmented generation, controllable and personalized responses, multi‑turn modeling, reinforcement‑learning strategies, low‑resource NLU, and data augmentation techniques.
The talk presents Didi AI Labs' research on intelligent dialogue robots for ride‑hailing, covering single‑turn QA, multi‑turn conversation, multi‑task learning architectures, model experiments, active learning pipelines, and the overall system design that integrates intent detection, slot extraction, dialogue management, and response generation.
This article reviews the evolution, architecture, and key technical challenges of general‑domain conversational QA systems, describing Alibaba UC’s search background, dialogue bot types, data pipelines, and advanced methods such as transfer learning, few‑shot learning, and multi‑dimensional dialogue management.
This comprehensive article explains reinforcement learning fundamentals, compares it with supervised learning, surveys Baidu's industrial RL applications such as recommendation, dialogue, prosthetics, and autonomous driving, introduces the open‑source PARL platform, and discusses current challenges and future research directions.
Tencent Xiaowei is an open, easy‑to‑integrate conversational AI platform that combines NLU, dialogue management and generation, supports multi‑turn context via Memory Networks, uses bidirectional RNN and CNN‑based intent classifiers, and powers smart speakers, TVs and customer‑service bots by leveraging Tencent’s rich content ecosystem.
The article reviews the inaugural global Task‑Oriented Multi‑Turn Dialogue Competition (JDDC), highlighting keynote speeches from JD.com executives, the competition’s dataset and evaluation methods, winning teams’ approaches, and future directions for AI‑driven conversational systems.
An extensive overview of ACL 2018, featuring acceptance statistics, award-winning papers, tutorial insights, and concise summaries of notable research across machine translation, semantic parsing, question answering, domain adaptation, text classification, summarization, dialogue systems, generation, and related tools.
This article reviews Alibaba's end‑to‑end intelligent dialogue system, detailing its connection‑driven interaction model, the core NLU framework, intent classification, attribute extraction, ranking, QA and chat modules, product deployments, and future research directions.
This article reviews the latest ACL research on deep‑learning‑driven natural‑language processing, covering advances in spoken dialogue policy optimization, retrieval‑based chatbots, information extraction, sentiment analysis, syntactic parsing efficiency, and word‑ and sentence‑vector techniques, highlighting key papers, datasets, and future challenges.
