Papers with variational autoencoders

10 papers
Controlled Text Generation Using Dictionary Prior in Variational Autoencoders (2022.findings-acl)

Copied to clipboard

Challenge: Variational autoencoders (VAEs) have been widely applied in text generation tasks, but they suffer from insufficient representation capacity and poor controllability.
Approach: They propose a data-driven prior that has expressivity and controllability.
Outcome: The proposed prior enjoys expressivity and controllability and can be used in language modeling and controlled text generation.
LangVAE and LangSpace: Building and Probing for Language Model VAEs (2025.emnlp-demos)

Copied to clipboard

Challenge: a novel framework for modular construction of variational autoencoders (VAEs) on pre-trained large language models (LLMs) is presented.
Approach: They propose a modular framework for variational autoencoders on top of pre-trained large language models.
Outcome: The proposed framework can encode pre-trained language models into more compact and semantically disentangled representations.
Disentangling Representations of Text by Masking Transformers (2021.emnlp-main)

Copied to clipboard

Challenge: Large pretrained models such as BERT encode a range of features into monolithic vectors, providing strong predictive accuracy across downstream tasks.
Approach: They explore whether it is possible to learn disentangled representations by identifying existing subnetworks within pretrained models that encode distinct, complementary aspects.
Outcome: The proposed method disentangles sentiment from genre in movie reviews, toxicity from dialect in Tweets, and syntax from semantics.
Generative Text Modeling through Short Run Inference (2021.eacl-main)

Copied to clipboard

Challenge: Latent variable models for text capture global semantic and syntactic features when trained correctly.
Approach: They propose a short run dynamics for inference that initializes from the prior distribution of the latent variable and runs a small number of Langevin dynamics steps guided by its posterior distribution.
Outcome: The proposed model is able to generate coherent sentences with smooth transition and shows no sign of posterior collapse.
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (P18-1)

Copied to clipboard

Challenge: Existing encoder-decoder dialog models cannot output interpretable actions as in traditional systems.
Approach: They propose an unsupervised discrete sentence representation learning method that integrates with existing encoder-decoder dialog models for interpretable response generation.
Outcome: The proposed model can be integrated with existing encoder-decoder dialog models and discover interpretable semantics via either auto encoding or context predicting.
Training Data Augmentation for Detecting Adverse Drug Reactions in User-Generated Content (D19-1)

Copied to clipboard

Challenge: Existing dictionary-based, semi-supervised learning approaches are limited by the coverage and maintainability of laymen health vocabularies.
Approach: They propose a data augmentation approach that leverages variational autoencoders to learn high-quality data distributions from a large unlabeled dataset and generate a small set of labeled training sets.
Outcome: The proposed approach matches the performance of fully-supervised approaches while requiring only 25% of training data.
vONTSS: vMF based semi-supervised neural topic modeling with optimal transport (2023.findings-acl)

Copied to clipboard

Challenge: Recent Neural Topic Models (NTMs) have limited applications in the real world due to the challenge of incorporating human knowledge.
Approach: They propose a semi-supervised neural topic modeling method, vONTSS, which uses von Mises-Fisher variational autoencoders and optimal transport.
Outcome: The proposed method outperforms existing semi-supervised topic modeling methods on multiple aspects.
Perceptual Models of Machine-Edited Text (2021.findings-acl)

Copied to clipboard

Challenge: a dataset of human judgments of machine-edited text is presented . we compare six different methods to create generic models of human perception .
Approach: They propose to use six machine-editing methods to model human perceptions of edited text . they use a dataset of human judgments of machine-edited text and scientific abstracts .
Outcome: The proposed model is based on human judgments of machine-edited text and scientific abstracts . human judgment of edited text is predicted to be within 6% of human consensus labeling .
Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation (D19-1)

Copied to clipboard

Challenge: Existing approaches to train variational autoencoders (VAEs) have been proposed to alleviate the posterior collapse issue in NLP tasks.
Approach: They propose to introduce a mutual information term between the input and its latent variable to regularize the objective of the VAE.
Outcome: The proposed model performs better on three benchmark datasets and is comparable to state-of-the-art models.
Spherical Latent Spaces for Stable Variational Autoencoders (D18-1)

Copied to clipboard

Challenge: Variational autoencoders use a multivariate Gaussian latent variable to capture latent structure in data.
Approach: They propose a variational autoencoder which uses a latent distribution instead of Gaussian . they find that the variational posterior averts the KL collapse by a fixed hyperparameter .
Outcome: The von Mises-Fisher distribution averts the KL collapse and gives better likelihoods than Gaussian models across a range of modeling conditions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations