0 views collected around this technical thread.
The article introduces the GPST unsupervised syntactic language model presented at ACL 2024, outlines its novel training approach, superior performance over GPT‑2, and provides details for a live online session where researcher Hu Xiang will discuss the work.
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 presents Tmall Genie’s end‑to‑end speech‑semantic understanding pipeline, detailing the limitations of traditional ASR‑NLU‑IR pipelines, introducing the Speech2Slot model with knowledge‑enhanced encoders, and describing unsupervised phoneme‑based pre‑training (Phoneme‑BERT) that improves entity extraction performance in voice‑driven content playback.