An Overview on Controllable Text Generation via Variational Auto-Encoders
Not on the map. Why?
Abstract (arXiv)
Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans and able to understand natural language. The employment of deep neural architectures has been largely explored in a multitude of context and tasks to fulfill various user needs. On one hand, producing textual content that meets specific requirements is of priority for a model to seamlessly conduct conversations with different groups of people. On the other hand, latent variable models (LVM) such as variational auto-encoders (VAEs) as one of the most popular genres of generative models are designed to characterize the distributional pattern of textual data. Thus they are inherently capable of learning the integral textual features that are worth exploring for controllable pursuits. noindent This overview gives an introduction to existing generation schemes, problems associated with text variational auto-encoders, and a review of several applications about the controllable generation that are instantiations of these general formulations,footnoteA detailed paper list is available at urlhttps://github.com/ImKeTT/CTG-latentAEs as well as related datasets, metrics and discussions for future researches. Hopefully, this overview will provide an overview of living questions, popular methodologies and raw thoughts for controllable language generation under the scope of variational auto-encoder.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 68 of its 97 references that are in the map. First posted on arXiv 15 Nov 2022.
Builds on
68 of 97 references.
References · 68
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2017Neural Discrete Representation Learningcited by 4,650
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
- 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
38 more
- 2015Generating Sentences from a Continuous Spacecited by 607
- 2013Generating Sequences With Recurrent Neural Networkscited by 549
- 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
- 2015Variational Dropout and the Local Reparameterization Trickcited by 489
- 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
- 2015Importance Weighted Autoencoderscited by 454
- 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
- 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
- 2015Adversarial Autoencoderscited by 359
- 2017Toward Controlled Generation of Textcited by 271
- 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
- 2017Challenges in Data-to-Document Generationcited by 226
- 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
- 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
- 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
- 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
- 2017Style Transfer in Text: Exploration and Evaluationcited by 145
- 2017InfoVAE: Information Maximizing Variational Autoencoderscited by 124
- 2020Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Spacecited by 114
- 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
- 2017Improved Variational Autoencoders for Text Modeling using Dilated Convolutionscited by 81
- 2014Grammar as a Foreign Languagecited by 70
- 2019Long and Diverse Text Generation with Planning-based Hierarchical Variational Modelcited by 62
- 2018Learning Neural Templates for Text Generationcited by 61
- 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
- 2017Adversarial Feature Matching for Text Generationcited by 58
- 2020Improving Disentangled Text Representation Learning with Information-Theoretic Guidancecited by 52
- 2018Content preserving text generation with attribute controlscited by 47
- 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
- 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
- 2016Improving Variational Auto-Encoders using Householder Flowcited by 41
- 2016Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversationcited by 35
- 2019Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representationcited by 34
- 2017A Hybrid Convolutional Variational Autoencoder for Text Generationcited by 33
- 2019A Surprisingly Effective Fix for Deep Latent Variable Modeling of Textcited by 32
- 2016The Generalized Reparameterization Gradientcited by 30
- 2019Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoderscited by 27
- 2019Implicit Deep Latent Variable Models for Text Generationcited by 26
50 most cited of 68 All 68 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.
- 2024Deep Autoregressive Models as Causal Inference Enginescited by 6
- 2024Deep Autoregressive Models as Causal Inference Engines27 Sep 2024