Sequence to Better Sequence: Continuous Revision of Combinatorial Structures

By Jonas W. Mueller, David K. Gifford, Tommi S. Jaakkola. 2017

100 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

Junction Tree Variational Autoencoder for Molecular Graph Generation (2018, methodology): “To optimize a molecule m , we start from its latent representation, and apply gradient ascent in the latent space to improve the predicted score F ( · ) , similar to (Mueller et al., 2017).”
Style Transfer in Text: Exploration and Evaluation (2017, background): “Mueller, Gifford, and Jaakkola (2017) proposed a variational auto-encoder (VAE) based model to revise a new sequence to improve its associated outcome.”
Style Transfer from Non-Parallel Text by Cross-Alignment (2017, background): “For instance, Mueller et al. (2017) manipulate the hidden representation to generate sentences that satisfy a desired property (e.g., sentiment) as measured by a corresponding classifier.”
A Survey on Bayesian Deep Learning (2016, methodology): “For example, [77] and [69] build on top of the BDL principles to define a language revision process.”
Adversarially Regularized Autoencoders (2017, result): “Finally, our work adds to the recent line of work on unaligned style transfer for text (Hu et al., 2017; Mueller et al., 2017; Li et al., 2018; Prabhumoye et al., 2018; Yang et al., 2018).”
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning (2019, methodology): “Similar ideas have been proposed in (Mueller, Gifford, and Jaakkola 2017; Luo et al. 2018) for sentence revision and neural architecture search.”
Polite Dialogue Generation Without Parallel Data (2018, methodology): “t al., 2017; Liu and Tuzel, 2016; Liu et al., 2017; Taigman et al., 2016; Kim et al., 2017; Yi et al., 2017), and text (Sennrich et al., 2016a; Hu et al., 2017; Ghosh et al., 2017; Zhao et al., 2017; Mueller et al., 2017; Wang et al., 2017; Luan et al., 2017). Among these models, some are bag-of-wor”
Adversarial Decomposition of Text Representation (2018, methodology): “Most importantly, in contrast to the proposals by Mueller et al. (2017), Hu et al. (2017), Kim et al. (2017), Fu et al. (2017), our model produces a representation for both meaning and form and does not treat the form as a categorical (in the vast majority of works, binary) variable.”
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation (2019, background): “In the past few years, attribute-controlled NLG has witnessed renewed interest by researchers working on neural approaches to generation (Hu et al., 2017; Jhamtani et al., 2017; Melnyk et al., 2017; Mueller et al., 2017; Zhang et al., 2018; Prabhumoye et al., 2018; Niu and Bansal, 2018).”
Fair Transfer of Multiple Style Attributes in Text (2019, methodology): “[8] proposed a technique that uses a variational auto-encoder to generate a revise sequence by manipulating the hidden representation.”
Text Style Transfer: A Review and Experiment Evaluation (2020, methodology): “[54] explored manipulating the hidden representation learned using VAE to generate sentences that contain a certain style measured using a corresponding classifier.”
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs (2019, result): “This methodology is very similar to that of Gómez-Bombarelli et al. [2], Jin et al. [14] for molecule optimization; also similar to Mueller et al. [36] for slightly revising a sentence.”