Deep belief nets for natural language call-routing

By Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabhadran. 2011

144 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jianfeng Gao
2. Li Deng
3. Xiaodong He
4. Bing Liu
5. Dong Yu
6. Yoshua Bengio
7. Erik Cambria
8. Mohit Bansal

In Computer Vision and Pattern Recognition

1. Jianfeng Gao
2. Li Deng
3. Xiaodong He
4. Luc Van Gool
5. Yoshua Bengio
6. Trevor Darrell
7. Dacheng Tao
8. Xiaogang Wang

In Signal Processing

1. Li Deng
2. Dong Yu
3. Xiaodong He
4. Yoshua Bengio
5. Jinyu Li
6. Jianfeng Gao
7. Gökhan Tür
8. Dilek Z. Hakkani-Tür

Citations in the corpus

• Deep Learning: Methods and Applications (2014, methodology): “[318] applied DNNs (called DBNs in the paper) to perform a natural language call–routing task.”
• Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling (2016, background): “Intent detection can be treated as a semantic utterance classification problem, and popular classifiers like support vector machines (SVMs) [1] and deep neural network methods [2] can be applied.”
• A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, positive): “g of a sequence of words, and the output is a sequence of slot/concept IDs, one for each word. [17] and [15] used deep belief networks (DBNs), and achieved superior results compared to CRF baselines. [51; 115; 66; 113] applied RNN for slot filling. The semantic representation generated by NLU is furt”
• Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Sarikaya et al. (2011) used a DBN-initialized neural network to complete slot filling in the call-routing task.”
• Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding (2015, background): “some preliminary SLU experiments [15], [24], [30], [56], in this”
• Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM (2016, methodology): “With the advances on deep learning, deep belief networks (DBNs) with deep neural networks (DNNs) have first been employed for intent determination in call centers [15], and later for domain classification in personal assistants [16, 17, 18].”
• Convolutional neural network based triangular CRF for joint intent detection and slot filling (2013, methodology): “The intent classification component in our proposed NN architecture (Figure 3) differs from the NN based intent classifier introduced in [4], in which case the word sequence is first converted into a feature vector (e.”
• A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding (2016, methodology): “The initial try is deep belief networks (DBNs), which have been used in call routing classification [Sarikaya et al., 2011] and slot filling [Deoras and Sarikaya, 2013].”
• Towards deeper understanding: Deep convex networks for semantic utterance classification (2012, methodology): “We did not experiment with other classification algorithms, as Boosting has already been shown to give comparable results [6, 18].”
• A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding (2019, methodology): “The intent detection is formulated as an utterance classi-fication problem, and different classification meth-ods, such as support vector machine (SVM) and RNN (Haffner et al., 2003; Sarikaya et al., 2011), has proposed to solve it.”
• A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling (2018, methodology): “The intent detection is treated as an utterance classification problem, which can be modeled using conventional classifiers including regression, support vector machines (SVMs) or even deep neural networks (Haffner et al., 2003; Sarikaya et al., 2011).”