REVIEW 13 cited by
Generating Sentences from a Continuous Space
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Generating Sentences from a Continuous Space
read the original abstract
The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple deterministic decoding. By examining paths through this latent space, we are able to generate coherent novel sentences that interpolate between known sentences. We present techniques for solving the difficult learning problem presented by this model, demonstrate its effectiveness in imputing missing words, explore many interesting properties of the model's latent sentence space, and present negative results on the use of the model in language modeling.
Forward citations
Cited by 13 Pith papers
-
Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation
Introduces textual belief states and factorized GRPO to enforce strict latent state mediation in text-based world models, yielding preserved prediction accuracy with large gains in representation quality and rollout p...
-
Density estimation using Real NVP
Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven gener...
-
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
T5 casts all NLP tasks as text-to-text generation, systematically explores pre-training choices, and reaches strong performance on summarization, QA, classification and other tasks via large-scale training on the Colo...
-
Language Models as Knowledge Bases?
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
-
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Hugging Face releases an open-source Python library that supplies a unified API and pretrained weights for major Transformer architectures used in natural language processing.
-
A Deep Generative Model for Code-Switched Text
VACS is a two-level hierarchical VAE that generates diverse code-switched sentences, and augmenting monolingual data with its output reduces language model perplexity by 33.06%.
-
Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer
Quantum annealing combined with a Neural Hash Function lets generative models create molecules that are more drug-like than classical versions or the training set itself.
-
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
VADD augments masked diffusion models with an auxiliary recognition model and variational inference to implicitly model inter-dimensional correlations, yielding higher-quality samples than standard MDMs at low denoisi...
-
I Am Not What I Write: Privacy Preserving Text Representation Learning
DPText learns text representations that are differentially private, free of private attributes, and retain utility for NLP tasks.
-
MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
MIDI-Sandwich is a hierarchical VAE-GAN architecture that generates structured 136-beat melodies by modeling local bars and global relationships on the Nottingham dataset.
-
On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data
Extends Social-STGCNN with CVAE for multimodal trajectory prediction and reports moderate gains plus better diversity on ETH/UCY benchmarks and robot data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.