Stacked Sequential Learning

By William W. Cohen, Vitor R. Carvalho. 2005

126 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.

Citations in the corpus

Deep Learning: Methods and Applications (2014, methodology): “In [60], the simple module used for stacking was a conditional random field (CRF).”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, methodology): “In [160], the simple module used for stacking was a CRF.”
Pose Machines: Articulated Pose Estimation via Inference Machines (2014, methodology): “Methods such as [23,24] applied sequential prediction to natural language processing tasks.”
Efficient Reductions for Imitation Learning (2010, methodology): “This is similar to the Sequential Stacking algorithm (Cohen 2005) for sequence classiﬁcation.”
Learning with Recursive Perceptual Representations (2012, methodology): “Cohen and de Carvalho [5] developed a stacking architecture where the simple module is a Conditional Random Field.”
Automatic Creation of Semantically Rich 3D Building Models from Laser Scanner Data (2011, methodology): “It has been successfully used in various applications, such as natural language processing (Cohen, 2005; Kou, 2007) and computer vision (Munoz et al.”
Pushing the Limits of Translation Quality Estimation (2017, background): “Stacking architectures (Wolpert, 1992; Breiman, 1996) have proved effective in structured NLP problems (Cohen and de Carvalho, 2005; Martins et al., 2008).”
A Review of Deep Learning Models for Time Series Prediction (2019, background): “The DSN was also reported to be connected with a Conditional Random Field (CRF), which was successfully developed and applied for Natural Language Processing (NLP) [126].”
Stacked Hierarchical Labeling (2010, methodology): “We build on the forward sequential learning approach used and analyzed in [28,10,25] to prevent cascading errors and leverage the sequential stacking idea to minimize cascaded overfitting [30,4,15].”
Composition of Conditional Random Fields for Transfer Learning (2005, unknown): “Finally, stacked sequential learning ( Cohen & Carvalho, 2005 ) is another potential method for combining the results of the subtask transducers.”
Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation (2019, methodology): “own predictions at inference. As a result, errors can accumulate along the generated sequence at inference time. This is a well-known issue in sequential decision making (Langford and Zadrozny, 2005; Cohen and Carvalho, 2005; Ka¨¨ari ainen and Lang-¨ ford, 2006, i.a.) and it has been addressed in pa”
Training Deterministic Parsers with Non-Deterministic Oracles (2013, background): “Other related approaches in the machine learning literature include stacked sequential learning (Cohen and Carvalho, 2005), LaSO (Daumé III and Marcu, 2005), Searn (Daumé III et al.”
Scalable stacking and learning for building deep architectures (2012, background): “Cohen and de Carvalho [7] successfully stacked CRFs to emulate long-range inference in NLP. Similarly stacked, deep-CRF was used in speech processing [8].”