Вариационный Вывод
Related Papers
The Infinite PCFG Using Hierarchical Dirichlet Processes
We present a nonparametric Bayesian model of tree structures based on the hierarchical Dirichlet process (HDP). Our HDP-PCFG model allows the complexity of the grammar to grow as more training …...
Improved Bayesian Logistic Supervised Topic Models with Data Augmentation
Supervised topic models with a logistic likelihood have two issues that potential- ly limit their practical use: 1) response variables are usually over-weighted by document word counts; and 2) existing …...
Generative Topic Embedding: a Continuous Representation of Documents
Word embedding maps words into a low- dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps …...
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation
AbstractParaphrase generation aims to generate semantically consistent sentences with different syntactic realizations. Most of the recent studies rely on the typical encoder-decoder framework where the generation process is deterministic. However, …...
AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
AbstractThe linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches. Exact probabilistic inference algorithms such as the forward-backward and Viterbi algorithms are typically …...
Narrative Text Generation with a Latent Discrete Plan
AbstractPast work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first …...
Topic Modeling in Embedding Spaces
AbstractTopic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we …...
VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling
AbstractIn this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, …...
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
AbstractMost combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task–language …...
TAN-NTM: Topic Attention Networks for Neural Topic Modeling
AbstractTopic models have been widely used to learn text representations and gain insight into document corpora. To perform topic discovery, most existing neural models either take document bag-of-words (BoW) or …...
Heterogeneous Supervised Topic Models
AbstractResearchers in the social sciences are often interested in the relationship between text and an outcome of interest, where the goal is to both uncover latent patterns in the text …...