This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response generation.Traditional methods usually adopt a supervised paradigm to learn DST from a manu...This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response generation.Traditional methods usually adopt a supervised paradigm to learn DST from a manually labeled corpus.However,the annotation of the corpus is costly,time-consuming,and cannot cover a wide range of domains in the real world.To solve this problem,we propose a multi-span prediction network(MSPN)that performs unsupervised DST for end-to-end task-oriented dialogue.Specifically,MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as keywords.Based on these keywords,MSPN uses a semantic distance based clustering approach to obtain the values of each slot.In addition,we propose an ontology-based reinforcement learning approach,which employs the values of each slot to train MSPN to generate relevant values.Experimental results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant improvements.Besides,we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain,which further demonstrates the adaptability of MSPN.展开更多
对话状态追踪(DST)是任务型对话系统中一个重要的模块,但现有的基于开放词表的DST模型没有充分利用槽位的相关信息以及数据集本身的结构信息。针对上述问题,提出基于槽位相关信息提取的DST模型SCELDST(SCE and LOW for Dialogue State T...对话状态追踪(DST)是任务型对话系统中一个重要的模块,但现有的基于开放词表的DST模型没有充分利用槽位的相关信息以及数据集本身的结构信息。针对上述问题,提出基于槽位相关信息提取的DST模型SCELDST(SCE and LOW for Dialogue State Tracking)。首先,构建槽位相关信息提取器(SCE),利用注意力机制学习槽位之间的相关信息;然后,在训练过程中应用学习最优样本权重(LOW)策略,在未大幅增加训练时间的前提下,加强模型对数据集信息的利用;最后,优化模型细节,搭建完整的SCEL-DST模型。实验结果表明,SCE和LOW对SCEL-DST模型性能的提升至关重要,该模型在两个实验数据集上均取得了更高的联合目标准确率,其中在MultiWOZ 2.3(Wizard-of-OZ 2.3)数据集上与相同条件下的TripPy(Triple coPy)相比提升了1.6个百分点,在WOZ 2.0(Wizard-of-OZ 2.0)数据集上与AG-DST(Amendable Generation for Dialogue State Tracking)相比提升了2.0个百分点。展开更多
基金supported by the National Key Research and Development Program of China under Grant No.2020AAA0106400the National Natural Science Foundation of China under Grant Nos.61922085 and 61976211+2 种基金the Independent Research Project of National Laboratory of Pattern Recognition under Grant No.Z-2018013the Key Research Program of Chinese Academy of Sciences(CAS)under Grant No.ZDBS-SSW-JSC006the Youth Innovation Promotion Association CAS under Grant No.201912.
文摘This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response generation.Traditional methods usually adopt a supervised paradigm to learn DST from a manually labeled corpus.However,the annotation of the corpus is costly,time-consuming,and cannot cover a wide range of domains in the real world.To solve this problem,we propose a multi-span prediction network(MSPN)that performs unsupervised DST for end-to-end task-oriented dialogue.Specifically,MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as keywords.Based on these keywords,MSPN uses a semantic distance based clustering approach to obtain the values of each slot.In addition,we propose an ontology-based reinforcement learning approach,which employs the values of each slot to train MSPN to generate relevant values.Experimental results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant improvements.Besides,we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain,which further demonstrates the adaptability of MSPN.
文摘对话状态追踪(DST)是任务型对话系统中一个重要的模块,但现有的基于开放词表的DST模型没有充分利用槽位的相关信息以及数据集本身的结构信息。针对上述问题,提出基于槽位相关信息提取的DST模型SCELDST(SCE and LOW for Dialogue State Tracking)。首先,构建槽位相关信息提取器(SCE),利用注意力机制学习槽位之间的相关信息;然后,在训练过程中应用学习最优样本权重(LOW)策略,在未大幅增加训练时间的前提下,加强模型对数据集信息的利用;最后,优化模型细节,搭建完整的SCEL-DST模型。实验结果表明,SCE和LOW对SCEL-DST模型性能的提升至关重要,该模型在两个实验数据集上均取得了更高的联合目标准确率,其中在MultiWOZ 2.3(Wizard-of-OZ 2.3)数据集上与相同条件下的TripPy(Triple coPy)相比提升了1.6个百分点,在WOZ 2.0(Wizard-of-OZ 2.0)数据集上与AG-DST(Amendable Generation for Dialogue State Tracking)相比提升了2.0个百分点。
