提出生成式框架，同时解决多意图识别与槽位填充问题。
A Generative Model for Joint Multiple Intent Detection and Slot Filling
- 用注意力叠加解码器处理可变数量意图及任务间干扰。
- 在MixATIS和MixSNIPS上达到当前最佳性能。
- 基于BERT的NSP头构建新多意图数据集，适合实际对话场景研究。
在任务导向对话系统中，口语理解（SLU）是关键组件，包含意图检测和槽位填充两个子任务。现有方法主要关注单意图场景，即每个语句仅有一个意图。然而真实场景中用户常在一个语句中表达多个意图，这对现有对话系统和数据集构成挑战。本文提出一种生成式框架，同时解决多意图检测与槽位填充问题。具体地，设计了一种注意力叠加解码器，通过引入归纳偏置，有效处理意图数量可变及两任务间的干扰。此外，利用BERT模型的下一句预测（NSP）头，基于已有单意图语句构建了两个新的多意图SLU数据集。实验表明，所提出的注意力叠加生成模型在两个公开数据集MixATIS、MixSNIPS以及自建数据集上均取得领先性能。
原文摘要 · Abstract (English)
In task-oriented dialogue systems, spoken language understanding (SLU) is a critical component, which consists of two sub-tasks, intent detection and slot filling. Most existing methods focus on the single-intent SLU, where each utterance only has one intent. However, in real-world scenarios users usually express multiple intents in an utterance, which poses a challenge for existing dialogue systems and datasets. In this paper, we propose a generative framework to simultaneously address multiple intent detection and slot filling. In particular, an attention-over-attention decoder is proposed to handle the variable number of intents and the interference between the two sub-tasks by incorporating an inductive bias into the process of multi-task learning. Besides, we construct two new multi-intent SLU datasets based on single-intent utterances by taking advantage of the next sentence prediction (NSP) head of the BERT model. Experimental results demonstrate that our proposed attention-over-attention generative model achieves state-of-the-art performance on two public datasets, MixATIS and MixSNIPS, and our constructed datasets.
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。