paper-with-me

홈 › Papers

A Tutorial on Deep Latent Variable Models of Natural Language

2018-12-17 · Yoon Kim, Sam Wiseman, Alexander M. Rush

There has been much recent, exciting work on combining the complementary strengths of latent variable models and deep learning. Latent variable modeling makes it easy to explicitly specify model constraints through conditional independence properties, while deep learning makes it possible to parameterize these conditional likelihoods with powerful function approximators. While these "deep latent variable" models provide a rich, flexible framework for modeling many real-world phenomena, difficulties exist: deep parameterizations of conditional likelihoods usually make posterior inference intractable, and latent variable objectives often complicate backpropagation by introducing points of non-differentiability. This tutorial explores these issues in depth through the lens of variational inference.

📄 PDF Abstract BibTeX arXiv:1812.06834

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningVariational Inference

Similar Papers 제목 키워드 기반

Training Latent Variable Models with Auto-encoding Variational Bayes: A Tutorial

2022-08-16 · Yang Zhi-Han

Auto-encoding Variational Bayes (AEVB) is a powerful and general algorithm for fitting latent variable models (a promising direction for unsupervised learning), and is well-known for training the Variational Auto-Encoder…

Variational Inference

A Unified Framework for Structured Prediction: From Theory to Practice

2017-09-01 · EMNLP 2017 9 · Wei Lu

Structured prediction is one of the most important topics in various fields, including machine learning, computer vision, natural language processing (NLP) and bioinformatics. In this tutorial, we present a novel framewo…

AMR ParsingChunkingPredictionSemantic Parsing+3

Latent Structure Models for Natural Language Processing

2019-07-01 · ACL 2019 7 · Andr{\'e} F. T. Martins, Tsvetomila Mihaylova, Nikita Nangia, Vlad Niculae

Latent structure models are a powerful tool for modeling compositional data, discovering linguistic structure, and building NLP pipelines. They are appealing for two main reasons: they allow incorporating structural bias…

Language ModelingLanguage ModellingMachine TranslationNatural Language Inference+4

An Introduction to Conditional Random Fields

2010-11-17 · Charles Sutton, Andrew McCallum

Often we wish to predict a large number of variables that depend on each other as well as on other observed variables. Structured prediction methods are essentially a combination of classification and graphical modeling,…

General Classificationparameter estimationPredictionStructured Prediction

An Introduction to Discrete Variational Autoencoders

2025-05-15 · Alan Jeffares, Liyuan Liu

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed la…

Decoder