arXiv cs.CL· Bing-Long Kuo, Yu-Hsuan Fang, Tien-Hong Lo, Hsueh-Wei Liao, Berlin Chen·· 11 小时前AI 评分22
APEX：用查询自适应意图检测提升口语理解检索效果
An Effective Spoken Language Understanding Approach Leveraging Query-Adaptive Intent Detection
AI 导读
论文提出 APEX 两阶段检索框架，先用意图级原型筛选候选意图，再在选定意图空间内检索上下文示例，以解决直接查询检索易选中语义相似但意图无关示例的问题。在 SLURP 数据集全转录条件下，APEX 搭配 Qwen3 4B 和 Gemma-3-4B 分别将 EMA 提升 4.34 和 3.97 个百分点；高困惑度输入下增益为 7.66 和 2.13 个百分点。
正文 · 原文
Abstract:Large language models enable fine-tuning-free spoken language understanding (SLU) through in-context learning, but direct query-based retrieval may select semantically similar yet intent irrelevant demonstrations. This paper presents Query-Adaptive Intent Detection via Prototype Extraction (APEX), a two-stage retrieval framework that first selects candidate intents using intent-level prototypes and then retrieves contextual exemplars within the selected intent space. Experiments on the SLURP dataset evaluate joint SLU performance using Exact Match Accuracy (EMA) under full-transcript and perplexity-stratified conditions, with additional retrieval analysis on ASR-generated transcripts. Compared with query-based retrieval, APEX improves EMA by 4.34 and 3.97 percentage points with Qwen3 4B and Gemma-3-4B, respectively, on full transcripts. Under high-perplexity inputs, APEX also yields EMA gains of 7.66 and 2.13 percentage points. Retrieval analysis further indicates that prototype-guided candidate selection achieves higher ground truth intent coverage across multiple input conditions.
| Comments: | Accepted for oral presentation at TAAI 2026. 6 pages |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.09491 [cs.CL] |
| (or arXiv:2611.09491v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.09491 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bing-Long Kuo [view email]
[v1]
Fri, 6 Nov 2026 14:13:17 UTC (785 KB)
来源：arXiv cs.CL · arxiv.org