Application of Deep Belief Networks for Natural Language Understanding

By Ruhi Sarikaya, Geoffrey E. Hinton, Anoop Deoras. IEEE/ACM Transactions on Audio Speech and Language Processing, 2014

457 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/c8933a793d5c2b423c2053cb2a0e1ec243ab6071

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

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Neural Approaches to Conversational AI (2018, unknown): “are often framed as a classiﬁcation problem, which infers the domain or intent (from a predeﬁned set of candidates) based on the current user utterance (Schapire and Singer, 2000; Yaman et al., 2008; Sarikaya et al., 2014). Neural approaches to multi-class classiﬁcation have been used in the recent ”
Automatically Learning Semantic Features for Defect Prediction (2016, methodology): “Existing work that leveraged DBN to generate features for NLP [55] and image recognition [6,25] reported that the performance of DBN-generated features is sensitive to these parameters.”
Financial Time Series Prediction Based on Deep Learning (2017, methodology): “And these algorithms have been widely and successfully used in many fields of artificial intelligence, such as image recognition [2], natural language processing [3], driver-less car and so on.”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “To solve the difficulty of training a deep neural network for domain and intent prediction, Restricted Boltzmann Machine (RBM) and Deep Belief Networks (DBNs) were applied to initialize the parameters of deep neural networks (Sarikaya et al., 2014).”
A Survey of Deep Learning Methods for Cyber Security (2019, background): “…types of networks have shown success in a number of applications, including acoustic modeling [23], speech recognition [24], and image recognition [25]. of networks have shown success in a number of applications, including acoustic modeling [23], speech recognition [24], and image recognition [25].”
Domain Generalization via Gradient Surgery (2021, background): “Deep learning models have shown remarkable results in diverse application areas such as image understanding [13, 28], speech recognition [10, 19] and natural language processing [24, 26].”
Fault Diagnosis for Rotating Machinery Using Multiple Sensors and Convolutional Neural Networks (2018, background): “Number of filters 64 128 Size of filter [3, 17, 1] [1, 8, 64] Stride 1 1 Dropout ratio 0.”
Cambricon: An Instruction Set Architecture for Neural Networks (2016, background): “For example, Deep Belief Networks (DBNs) [41] consist of a sequence of layers, each of which is fully connected to its adjacent layers.”
FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review (2019, background): “, in Google Now, Siri, or click-through prediction on an advertisement) [18]–[20], document processing [21]–[23], natural language processing [24], [25], video classification [26],”
End-to-End Learning of Task-Oriented Dialogs (2018, background): “Wen et al. (Wen et al., 2017) proposed an end-to-end trainable neural dialog model with modularly connected system components for SLU, DST, and dialog policy.”
Deep Learning for EMG-based Human-Machine Interaction: A Review (2021, unknown): “The DBN has many applications, such as health diagnosis [31], speech recognition [32], and natural language processing [33].”
The Technology Behind Personal Digital Assistants: An overview of the system architecture and key components (2017, methodology): “Typically, support vector machines, boosted decision trees, maximum entropy models [35], or neural networks [13], [33], [34] are used for modeling.”
Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition (2019, background): “Currently, DBN is applying for natural language understanding with significant success [123].”
Deep Learning and Its Applications in Biomedicine (2018, background): “For instance, deep belief networks (DBNs) and stacks of restricted Boltzmann machines (RBMs) [3,48,49] have been applied in speech and image recognition [3,45,50] and natural language processing [51].”
FP-DNN: An Automated Framework for Mapping Deep Neural Networks onto FPGAs with RTL-HLS Hybrid Templates (2017, background): “DNNs have brought in profound and revolutionary changes to the realm of artificial intelligence, and achieved great improvements in many domains such as computer vision [22] [13] [15], speech recognition [9], natural language processing [20], etc.”
Sparse Adversarial Attack via Perturbation Factorization (2020, methodology): “However, the 100% ASR values of C&W-(cid:96) 0 and our method tell that the above adversarial training is still not robust enough to defend the sparse attack.”
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].”