用MiniLM嵌入构建多簇边界，提升未知意图检测准确率
A Multi-cluster Boundary Learning Method for Out-of-Scope Intent Detection via MiniLM Embedding
- 将未知意图检测转为单类分类，利用MiniLM学习多簇嵌入边界
- 在CLINC150等数据集上达到当前最优性能，准确率显著提升
- 轻量级模型适合实际部署，特别适合资源受限场景
意图检测是人机交互系统中连接用户意图与系统动作的关键任务。然而，对未知范围（OOS）意图的检测仍面临挑战：(i) 传统方法将OOS检测视为多分类，已知意图类别越多，准确率越低；(ii) 大语言模型嵌入方法参数量大，难以训练和部署。为此，本文提出一种基于MiniLM嵌入（all-MiniLM-L6-v2）的多簇边界学习方法，在单类分类框架下实现OOS意图检测。该方法从训练语句中学习多簇嵌入边界，进而将跨域语句识别为OOS意图。在公开数据集CLINC150、StackOverflow和Banking77上进行实验，结果表明该方法优于现有基线，达到当前最优性能。消融实验显示，MiniLM更适应该流程与语句嵌入需求。代码见补充材料。
原文摘要 · Abstract (English)
Intent detection is a critical task that bridges human intents and system actions in human-machine interaction systems. However, there still exist challenges for detecting out-of-scope (OOS) intents. (i) The traditional methods view the OOS intent detection as a multi-class classification, then the detection accuracy decreases as the class number of the known intents increases; (ii) LLM-embedding methods require large parameters, that makes them difficult to train and practically deploy. Thus, this work proposes a multi-cluster boundary learning method to detect OOS intents via MiniLM embedding (i.e., all-MiniLM-L6-v2) in an one-class classification workflow. The method learns the boundaries of multi-cluster embeddings generated by MiniLM from the training utterances, and then rejects the out-of-domain utterances as OOS intents. Experiments are conducted on public CLINC150, StackOverflow and Banking77 datasets. The results show that the method achieves the state-of-the-art OOS intent detection performance compared the other baselines. Ablation studies are also conducted and the results show that the used MiniLM can better adapt to the workflow and utterance embedding requirements. The code is available at supplementary materials.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。