Use of kernel deep convex networks and end-to-end learning for spoken language understanding

L. Deng, Gökhan Tür, Xiaodong He, Dilek Z. Hakkani-Tür
{"title":"Use of kernel deep convex networks and end-to-end learning for spoken language understanding","authors":"L. Deng, Gökhan Tür, Xiaodong He, Dilek Z. Hakkani-Tür","doi":"10.1109/SLT.2012.6424224","DOIUrl":null,"url":null,"abstract":"We present our recent and ongoing work on applying deep learning techniques to spoken language understanding (SLU) problems. The previously developed deep convex network (DCN) is extended to its kernel version (K-DCN) where the number of hidden units in each DCN layer approaches infinity using the kernel trick. We report experimental results demonstrating dramatic error reduction achieved by the K-DCN over both the Boosting-based baseline and the DCN on a domain classification task of SLU, especially when a highly correlated set of features extracted from search query click logs are used. Not only can DCN and K-DCN be used as a domain or intent classifier for SLU, they can also be used as local, discriminative feature extractors for the slot filling task of SLU. The interface of K-DCN to slot filling systems via the softmax function is presented. Finally, we outline an end-to-end learning strategy for training the softmax parameters (and potentially all DCN and K-DCN parameters) where the learning objective can take any performance measure (e.g. the F-measure) for the full SLU system.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"114","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE Spoken Language Technology Workshop (SLT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SLT.2012.6424224","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 114

Abstract

We present our recent and ongoing work on applying deep learning techniques to spoken language understanding (SLU) problems. The previously developed deep convex network (DCN) is extended to its kernel version (K-DCN) where the number of hidden units in each DCN layer approaches infinity using the kernel trick. We report experimental results demonstrating dramatic error reduction achieved by the K-DCN over both the Boosting-based baseline and the DCN on a domain classification task of SLU, especially when a highly correlated set of features extracted from search query click logs are used. Not only can DCN and K-DCN be used as a domain or intent classifier for SLU, they can also be used as local, discriminative feature extractors for the slot filling task of SLU. The interface of K-DCN to slot filling systems via the softmax function is presented. Finally, we outline an end-to-end learning strategy for training the softmax parameters (and potentially all DCN and K-DCN parameters) where the learning objective can take any performance measure (e.g. the F-measure) for the full SLU system.
使用核深度凸网络和端到端学习口语理解
我们介绍了我们最近和正在进行的将深度学习技术应用于口语理解(SLU)问题的工作。将以前开发的深度凸网络(DCN)扩展到其内核版本(K-DCN),其中每个DCN层中的隐藏单元数量使用核技巧接近无穷大。我们报告的实验结果表明,K-DCN在基于boost的基线和DCN在SLU的域分类任务上实现了显着的误差减少,特别是当使用从搜索查询点击日志中提取的高度相关的特征集时。DCN和K-DCN不仅可以作为SLU的域或意图分类器,还可以作为SLU槽填充任务的局部判别特征提取器。给出了K-DCN通过softmax函数与槽位填充系统的接口。最后,我们概述了一个端到端学习策略,用于训练softmax参数(以及潜在的所有DCN和K-DCN参数),其中学习目标可以对整个SLU系统采取任何性能度量(例如f度量)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信