Deep belief nets for natural language call-routing

Sarikaya, Ruhi; Hinton, Geoffrey E.; Ramabhadran, Bhuvana

doi:10.1109/icassp.2011.5947649

Cited by 116 publications

(62 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Language Understanding With the advances on deep learning, deep belief networks (DBNs) with deep neural networks (DNNs) have been applied to domain and intent classification tasks (Sarikaya et al, 2011;Tur et al, 2012;Sarikaya et al, 2014). Recently, Ravuri and Stolcke (2015) proposed an RNN architecture for intent determination.…”

Section: Deep Learning Based Dialogue Systemmentioning

confidence: 99%

Deep Learning for Dialogue Systems

Chen¹,

Çelikyılmaz²,

Hakkani‐Tür³

2017

Proceedings of ACL 2017, Tutorial Abstracts

View full text Add to dashboard Cite

In the past decade, goal-oriented spoken dialogue systems have been the most prominent component in today's virtual personal assistants. The classic dialogue systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling. However, how to successfully apply deep learning based approaches to a dialogue system is still challenging. Hence, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building dialogue systems and summarizing the challenges, in order to allow researchers to study the potential improvements of the state-of-the-art dialogue systems. The tutorial material is available at http://deepdialogue. miulab.tw. Tutorial OverviewWith the rising trend of artificial intelligence, more and more devices have incorporated goal-oriented spoken dialogue systems. Among popular virtual personal assistants, Microsoft's Cortana, Apple's Siri, Amazon Alexa, Google Assistant, and Facebook's M, have incorporated dialogue system modules in various devices, which allow users to speak naturally in order to finish tasks more efficiently.The traditional conversational systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling. Nevertheless, applying deep learning technologies for building robust and scalable dialogue systems is still a challenging task and an open research area as it requires deeper understanding of the classic pipelines as well as detailed knowledge on the benchmark of the models of the prior work and the recent state-of-the-art work.The goal of this tutorial is to provide the audience with developing trend of the dialogue systems, and a roadmap to get them started with the related work. In the first section of the tutorial, we motivate the work on conversation-based intelligent agents, in which the core underlying system is task-oriented dialogue systems. The second and third sections describe different approaches using deep learning for each component in the dialogue system and how it is evaluated. The last two sections focus on discussing the recent trends and current challenges on dialogue system technology and summarize the challenges and conclusions. Then the detailed content is described as follows.2 Outline

show abstract

Section: Deep Learning Based Dialogue Systemmentioning

confidence: 99%

Deep Learning for Dialogue Systems

Chen¹,

Çelikyılmaz²,

Hakkani‐Tür³

2017

Proceedings of ACL 2017, Tutorial Abstracts

View full text Add to dashboard Cite

show abstract

“…The task includes classifying a user's series of utterances into corresponding words (speech recognition), assigning an appropriate semantic label related to the domain of concern to each word (semantic slot filling), and eventually classifying what user has meant from the series of utterances, i.e. a user's intent within the target domain (intent classification) [ , and Ho-Jin Choi 1 [13]. As the purpose of SLU systems is to aid the user with a particular task, e.g., viewing a flight schedule from A to B, it is assumed that users express their intent explicitly in their utterances.…”

Section: Introductionmentioning

confidence: 99%

Classifying Travel-related Intents in Textual Data

Kim

Jeong

Hyeon

et al. 2016

IJCCIE

View full text Add to dashboard Cite

Abstract-Intent classification refers to the process of identifying a set of intents of interest that appear in a given document. This work considers the task of annotating travel-related reviews with travel intents that best represent the reviewer's reason for visiting the place of interest (POI). A domain-tailored word embedding model is learned to construct intent-specific feature vectors, thereby improving classification accuracy. The feasibility of multiclass intent classification is explored using an intent corpus, consisting of 6,560 labelled reviews.

show abstract

“…While other NN architectures for semantic classification exist [11,12,13], we like to present this work in the context of CNN feeding off our previous experiences [14,15]. The choice of using CNN as opposed to others is not critical to the main theme of this work -recurrent connections can also be added to other NN based models.…”

Section: Convolutional Neural Network Based Domain Classificationmentioning

confidence: 99%

“…RNN was more recently proposed for the slot filling task in the SLU area [6,7], in which the task is to predict the slot tag for each word in the sequence. In addition to the success of using RNN, recent years have also witnessed the surge of interests in general NN based techniques for speech and language applications [8,9,10], some of them are specifically proposed for the utterance classification tasks in SLU, but limited to using features from the current turn [11,12,13].…”

Section: Introductionmentioning

confidence: 99%

Contextual domain classification in spoken language understanding systems using recurrent neural network

Sarikaya

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

In a multi-domain, multi-turn spoken language understanding session, information from the history often greatly reduces the ambiguity of the current turn. In this paper, we apply the recurrent neural network (RNN) to exploit contextual information for query domain classification. The Jordan-type RNN directly sends the vector of output distribution to the next query turn as additional input features to the convolutional neural network (CNN). We evaluate our approach against SVM with and without contextual features. On our contextually labeled dataset, we observe a 1.4% absolute (8.3% relative) improvement in classification error rate over the non-contextual SVM, and 0.9% absolute (5.5% relative) improvement over the contextual SVM.

show abstract

Deep belief nets for natural language call-routing

Cited by 116 publications

References 8 publications

Deep Learning for Dialogue Systems

Deep Learning for Dialogue Systems

Classifying Travel-related Intents in Textual Data

Contextual domain classification in spoken language understanding systems using recurrent neural network

Contact Info

Product

Resources

About