Conditional Neural Fields

By Jian Peng, Liefeng Bo, Jinbo Xu. 2009

173 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Structured Attention Networks (2017, background): “…applications, most notably in seminal work on graph transformers (LeCun et al., 1998), key work on NLP (Collobert et al., 2011), and in many other areas (Peng et al., 2009; Do & Arti´eres, 2010; Jaderberg et al., 2014; Chen et al., 2015; Durrett & Klein, 2015; Lample et al., 2016, inter alia ).”
Conditional Random Fields as Recurrent Neural Networks (2015, neutral): “[45] used a modified version of CRFs.”
Fully Connected Deep Structured Networks (2015, background): “More recently [5, 27, 22, 6, 28, 25] incorporate non-linearities into unary potentials but generally assume exact inference to be tractable.”
Learning Deep Structured Models (2014, background): “Conditional Neural Fields [21] extend Conditional Random Fields (CRFs) by augmenting the unary feature using a ‘gate function’ which combines different features in a non-linear manner.”
Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction (2014, background): “Other developments include better capturing spatial dependencies us-ing bidirectional recurrent neural networks (BRNN) (Baldi et al., 1999; Pollastri et al., 2002), probabilistic graphical models (Schmidler et al., 2000; Chu et al., 2004; van der Maaten et al., 2011), or combination of neural networ”
MRFalign: Protein Homology Detection through Alignment of Markov Random Fields (2014, methodology): “be placed here) Node alignment potential. Given an alignment path, its node alignment potential is the accumulative potential of all the vertices in the path. We use a Conditional Neural Fields (CNF) [40] method, which is very similar to what is described in the protein threading paper [41], to esti”
OptNet: Differentiable Optimization as a Layer in Neural Networks (2017, background): “…a strong push to further incorporate structured prediction methods like conditional random ﬁelds as the “last layer” of a deep network architecture (Peng et al., 2009; Zheng et al., 2015; Chen et al., 2015) as well as in deeper energy-based architectures (Belanger & McCallum, 2016; Belanger et…”
Globally Normalized Transition-Based Neural Networks (2016, methodology): “Smith and Johnson (2007) cite Michael Collins as the source of the example underlying the proof.”
Input Convex Neural Networks (2016, background): “In recent years, there has been a strong push to further incorporate structured prediction methods like conditional random ﬁelds as the “last layer” of a deep network architecture (Peng et al., 2009; Zheng et al., 2015; Chen et al., 2015).”
Template-based protein structure modeling using the RaptorX web server (2012, methodology): “The secondary structure prediction module is based on a CNF model 28 developed by Wang et al 47 .”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “Many of the discriminative techniques in signal and information processing apply to shallow architectures such as HMMs (e.g., [87–94]) or CRFs (e.g., [95–100]).”
Convolutional neural network based triangular CRF for joint intent detection and slot filling (2013, methodology): “In [8, 9], conditional neural field and neural CRF were introduced which combined the NN based feature learning and the CRF models.”
Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks (2017, background): “Recently, they have shown state-of-the-art results in segmentation [15, 16] when combined with deep neural networks [17, 18, 19].”
Effect of Non-linear Deep Architecture in Sequence Labeling (2013, methodology): “It was termed Conditional Neural Fields by Peng et al. (2009), and later Neural Conditional Random Fields by Do and Artieres (2010).”
Protein Homology Detection Through Alignment of Markov Random Fields (2015, methodology): “We use a Conditional Neural Fields (CNF) [12] method to develop such a node alignment potential, using a procedure very similar to what is described in the protein threading paper [13, 14].”
Deep neural network models for computational histopathology: A survey (2019, methodology): “These techniques have been extensively used in computer vision tasks for sequence labeling (Artieres et al., 2010; Peng et al., 2009) and semantic image segmentation problems (Chen et al.”
Segmental Recurrent Neural Networks (2015, methodology): “Finally, using neural networks to provide local features in conditional random field models has also been proposed for sequential models (Peng et al., 2009) and tree-structured models (Durrett & Klein, 2015).”