paper-with-me

홈 › Papers

Piecewise Latent Variables for Neural Variational Text Processing

2016-12-01 · EMNLP (ACL) 2017 9 · Iulian V. Serban, Alexander G. Ororbia II, Joelle Pineau, Aaron Courville

Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution. This distribution has the capacity to represent an exponential number of modes of a latent target distribution, while remaining mathematically tractable. Our results demonstrate that incorporating this new latent distribution into different models yields substantial improvements in natural language processing tasks such as document modeling and natural language generation for dialogue.

📄 PDF Abstract BibTeX arXiv:1612.00377

Code (2)

ago109/piecewise-nvdm-emnlp-2017 공식 구현
julianser/hred-latent-piecewise 공식 구현

Tasks

Text GenerationVariational Inference

Similar Papers 제목 키워드 기반

Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing

2026-04-14 · Danru Xu, Sébastien Lachapelle, Sara Magliacane arxiv

Causal representation learning (CRL) aims to identify the underlying latent variables from high-dimensional observations, even when variables are dependent with each other. We study this problem for latent variables that…

Representation Learning

Neural Variational Inference for Text Processing

2015-11-19 · Yishu Miao, Lei Yu, Phil Blunsom

Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of tex…

Answer SelectionQuestion AnsweringTopic ModelsVariational Inference

Self-supervised Latent Space Optimization with Nebula Variational Coding

2025-06-02 · Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari

Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, …

FormMetric LearningVariational Inference

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

2022-07-13 · NAACL 2022 7 · Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun 외

The past several years have witnessed Variational Auto-Encoder's superiority in various text generation tasks. However, due to the sequential nature of the text, auto-regressive decoders tend to ignore latent variables a…

DiversityText Generation

Better Exploiting Latent Variables in Text Modeling

2019-07-01 · ACL 2019 7 · Canasai Kruengkrai

We show that sampling latent variables multiple times at a gradient step helps in improving a variational autoencoder and propose a simple and effective method to better exploit these latent variables through hidden stat…