Detecting out-of-scope user utterances is essential for task-oriented
dialogues and intent classification. Current methodologies face difficulties
with the unpredictable distribution of outliers and often rely on assumptions
about data distributions. We present the Dual Encoder for Threshold-Based
Re-Classification (DETER) to address these challenges. This end-to-end
framework efficiently detects out-of-scope intents without requiring
assumptions on data distributions or additional post-processing steps. The core
of DETER utilizes dual text encoders, the Universal Sentence Encoder (USE) and
the Transformer-based Denoising AutoEncoder (TSDAE), to generate user utterance
embeddings, which are classified through a branched neural architecture.
Further, DETER generates synthetic outliers using self-supervision and
incorporates out-of-scope phrases from open-domain datasets. This approach
ensures a comprehensive training set for out-of-scope detection. Additionally,
a threshold-based re-classification mechanism refines the model's initial
predictions. Evaluations on the CLINC-150, Stackoverflow, and Banking77
datasets demonstrate DETER's efficacy. Our model outperforms previous
benchmarks, increasing up to 13% and 5% in F1 score for known and unknown
intents on CLINC-150 and Stackoverflow, and 16% for known and 24% % for unknown
intents on Banking77. The source code has been released at
this https URL

检测任务导向对话和意图分类中的超范围用户话语是至关重要的。我们提出了一种名为 DETER 的双编码器阈值重新分类的端到端框架，用于解决当前方法在处理异常值的不可预测分布上所面临的困难，并且不需要对数据分布或额外的后处理步骤做出假设。DETER 的核心利用双文本编码器 —— 通用句子编码器（USE）和基于 Transformer 的去噪自编码器（TSDAE），生成用户话语嵌入，通过分支神经架构进行分类。DETER 还利用自我监督生成合成异常值，并结合来自开放域数据集的超范围短语，确保了超范围检测的全面训练集。此外，基于阈值的重新分类机制对模型的初始预测进行细化。在 CLINC-150、Stackoverflow 和 Banking77 数据集上的评估证明了 DETER 的有效性，我们的模型在 CLINC-150 和 Stackoverflow 上的已知和未知意图的 F1 分数分别提高了 13% 和 5%，在 Banking77 上已知意图提高了 16%，未知意图提高了 24%。源代码已在此网址发布。