Learning Dialogue History for Spoken Language Understanding

摘要：

　　In task-oriented dialogue systems,spoken language understanding(SLU)aims to convert users queries expressed by natural language to structured representations.SLU usually consists of two parts,namely intent identification and slot filling.Although many methods have been proposed for SLU,these methods generally process each utterance individually,which loses context information in dialogues.In this paper,we propose a hierarchical LSTM based model for SLU.The dialogue history is memorized by a turn-level LSTM and it is used to assist the prediction of intent and slot tags.Consequently,the understanding of the current turn is dependent on the preceding turns.We conduct experiments on the NLPCC 2018 Shared Task 4 dataset.The results demonstrate that the dialogue history is effective for SLU and our model outperforms all baselines.

关键词： Spoken language understanding Dialogue history Hierarchical LSTM

作者: Xiaodong Zhang Dehong Ma Houfeng Wang

作者单位: Institute of Computational Linguistics,Peking University,Beijing 100871,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 120-132

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）