0 views collected around this technical thread.
Professor Wang Yichao from Huawei Noah's Ark Lab presents a comprehensive exploration of large language models in recommendation systems, covering background, challenges, two key projects (LLM4Rec and Uni-CTR), experimental results, and future directions for open, knowledge‑enhanced, generative recommendation pipelines.
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 report reviews the background, recent research progress, practical applications, and future directions of controllable text generation using transformer‑based pretrained language models, highlighting methods such as decoding strategies, prompt learning, memory networks, continual learning, contrastive training, and knowledge integration.
This talk presents recent year’s research on natural language generation, covering the ProphetNet pre‑trained generation model, external‑knowledge integration for generation, non‑autoregressive pre‑training (BANG), the Poolingformer long‑text architecture, EL‑attention for faster decoding, and a new multi‑task generation benchmark.
This article presents the business background of Tmall Genie’s voice‑driven content‑on‑demand service, critiques the traditional pipeline for entity extraction, and details an end‑to‑end speech‑semantic model—including the Speech2Slot architecture, knowledge‑enhanced encoding, and Phoneme‑BERT unsupervised pre‑training—demonstrating significant performance gains in both generation and classification tasks.
The article reviews recent research on multimodal digital content generation and automatic text summarization, outlining the evolution from extractive to abstractive methods, highlighting four key technology trends such as pretrained language models, transformer dominance, knowledge‑enhanced generation, and multimodal‑knowledge joint modeling, and describing an industrial e‑commerce application built on these advances.
This article provides a detailed survey of pre‑trained models (PTMs) for natural language processing, classifying them into shallow embeddings and contextual encoders, discussing training paradigms such as knowledge integration and model compression, and offering guidance on transfer learning and future challenges.