人机对话理解中联合学习技术的研究
首发时间:2017-01-05
摘要:对人机对话理解中的槽填充和意图识别任务建立联合学习模型,并将条件随机场和双向长短期记忆模型分别应用于该联合学习模型。通过实验确定在句子末尾添加意图标识符的建模方法,使用对话历史信息特征来提高联合学习模型的效果。不同大小训练集的对比实验表明,当前语料规模下基于条件随机场的联合学习模型效果更好,但随着语料规模的增大基于双向长短期记忆模型的联合学习模型效果增长趋势更明显。
关键词: 自然语言处理 人机对话理解 多任务 联合学习模型 条件随机场 长短期记忆模
For information in English, please click here
Research on Joint Learning Technology in Spoken Language Understanding
Abstract:A joint learning model is established for the slot filling and intention detection tasks in spoken dialogue understanding, the conditional random fields and bi-directional long short-term memory models are applied to the joint learning model. The method of adding the intention identifier at the end of the sentence is determined by experiments, and the effect of the joint learning model is improved by using the feResearch on Joint Learning Technology in Spoken Language Understandingature of the dialogue history information. The experiment results of different size of training set indicate that the joint learning model based on conditional random fields is better under the current corpus scale, but with the increase of the size of the corpus, the effect growth trend of joint learning model based bi-directional long short- term memory is more obvious.
Keywords: Natural language processing Spoken language understanding Multi tasks Joint learning model Conditional random fields Long short-term memory model
基金:
论文图表:
引用
No.4715369117627514****
同行评议
勘误表
人机对话理解中联合学习技术的研究
评论
全部评论0/1000