基于细粒度信息集成的意图识别和槽填充联合模型

Joint model of intent detection and slot filling based on fine-grained information integration

意图识别和槽位填充是构建口语理解(SLU)系统的两项主要任务,两者相互联合的模型是对话系统的研究热点。这两个任务紧密相连,槽位填充通常高度依赖于意图信息。针对最近联合模型中:固定阈值很难在不同领域中选择出正向的投票,且复杂的意图信息不能充分地引导槽位填充的问题。提出了一种基于细粒度信息集成的意图识别和槽填充联合模型。其中,将由意图解码器获取的意图信息与各单词的编码表示拼接,形成意图引导的集成编码表示,从而为单词级槽位填充提供细粒度的意图信息。同时,通过计算最大意图得分和最小意图得分的中间值获得逻辑自适应阈值,并用其代替固定阈值。逻辑自适应阈值可随不同意图标签的得分分布而变化。通过在两个多标签数据集上的实验结果验证了提出的模型的性能。

Intent detection and slot filling are two main tasks for building a spoken language understanding(SLU)system,the joint model of the two tasks is the research hotspot of the dialogue system.These two tasks are closely tied and the slots often highly depend on the intent.For the recent joint model:the fixed threshold is difficult to extract the positive votes in different domains.And the complex intent information guides the slot filling insufficiently.This paper proposed a fine-grained information integrated model for multiple intent detection and slot filling.Among this model,the intent information obtained by the intent decoder was concatenate with the encoding representation of each token to form an intent guided integrated encoding representation,so as to offer fine-grained intent information for the token-level slot prediction.At the same time,calculating the median of the maximum intent score and the minimum intent score to obtain the logic-adaptive threshold,and used it replace the fixed threshold.The logic-adaptive threshold can vary with the score distribution of different intent labels.Experimental results on two multi-label datasets verifies the performance of the proposed model.