Towards deeper understanding: Deep convex networks for semantic utterance classification

By Gökhan Tür, Li Deng, Dilek Z. Hakkani-Tür, Xiaodong He. 2012

132 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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. Li Deng
2. Dong Yu
3. Jianfeng Gao
4. Xiaodong He
5. Yoshua Bengio
6. Jinyu Li
7. Mohit Bansal
8. Percy Liang

In Signal Processing

1. Li Deng
2. Dong Yu
3. Jinyu Li
4. Yifan Gong
5. Yoshua Bengio
6. M. Seltzer
7. Xiaodong He
8. Frank Torsten Bernd Seide

Citations in the corpus

• Learning Continuous Phrase Representations for Translation Modeling (2014, methodology): “The objective function, which takes the form of the expected BLEU computed from N-best lists, is very different from the usual objective functions used in most existing architectures of neural networks, e.g., cross entropy (Hin-ton et al. 2012) or mean square error (Deng et al. 2012).”
• Semantic Parsing for Single-Relation Question Answering (2014, background): “In a separate line of research, deep learning based techniques have been proposed for semantic understanding (Mesnil et al., 2013; Huang et al., 2013; Shen et al., 2014b; Salakhutdinov and Hinton, 2009; Tur et al., 2012).”
• A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, methodology): “Deep learning techniques have been successively applied in intent detection [10; 73; 99].”
• Reconstructing Capsule Networks for Zero-shot Intent Classification (2019, background): “Conventional intent classification methods (Hu et al., 2009; Tur et al., 2012; Xu and Sarikaya, 2013; Ravuri and Stolcke, 2015; Liu and Lane, 2016; Nam et al., 2016) typically train a supervised learning model on large amounts of labeled data, and are not effective in recognizing emerging unseen int”
• Recent advances in deep learning for speech research at Microsoft (2013, methodology): “We have also explored the use of various versions of deep learning models for this task, with highly promising results reported in [15][50].”
• Ensemble deep learning: A review (2021, background): “2012 Towards deeper understanding: Deep convex networks for semantic utterance classification [203] Stacking Semantic Utterance Classification”
• 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].”
• Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding (2015, methodology): “As additional sets of experiments, we report results on two other custom datasets focusing on movies [39] and entertainment.”
• Parallel Training for Deep Stacking Networks (2012, background): “Since the birth of deep learning around 2006 [10][2][14], deep models with various types have recently been developed and successfully evaluated for a number of speech processing applications [3][4][7][11][ 15 ].”
• Learning semantic representations using convolutional neural networks for web search (2014, background): “In a separate line of research, deep learning based techniques have been proposed for semantic understanding[3][6][9][10].”
• Scalable stacking and learning for building deep architectures (2012, methodology): “In addition to the success of DSN as a powerful classifier on speech and image classification tasks presented in this paper, DSN has more recently been applied to speech understanding [13] with strong results.”
• Deep stacking networks for information retrieval (2013, background): “The simplicity of the DSN’s training objective drastically facilitates its successful applications to image recognition, speech recognition, and speech understanding [4][12].”
• Speech-Centric Information Processing: An Optimization-Oriented Approach (2013, background): “They could be appropriately placed either before or after the ASR stage in Fig.”
• Learning deep structured semantic models for web search using clickthrough data (2013, background): “Popular models can be grouped into two categories, linear projection models and generative topic models, which we will review in turn.”
• A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion (2013, background): “Some related DNN architectures have also demonstrated effectiveness in speech understanding and (small scale) image recognition tasks [7][9][35].”
• RC-NET: A General Framework for Incorporating Knowledge into Word Representations (2014, unknown): “Deep learning techniques have been frequently used to solve natural language processing (NLP) tasks [8, 1, 12, 21, 22].”
• Recent advances in deep learning based dialogue systems: a systematic survey (2021, background): “Deng et al. (2012) and Tur et al. (2012) were the first who successfully improved the recognition accuracy of dialogue intent.”
• Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding (2013, methodology): “Despite many years of research, the slot filling task in SLU is still a challenging problem, in parallel with the intent determination task [23][27].”