Research map / Probabilistic and scientific modeling / Variational and generative sampling
Document Neural Autoregressive Distribution Estimation
Stanislas Lauly, Yin Zheng, Alexandre Allauzen, Hugo Larochelle
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hidden layers to DeepDocNADE (1 to 3 layers) (ablation) | DeepDocNADE · 20 Newsgroups (50 topics) | test perplexity per word: 835 -> 877 -> 923 | Hurt |
| add hidden layers to DeepDocNADE (1 to 3 layers) (ablation) | DeepDocNADE · RCV1-V2 (50 topics) | test perplexity per word: 579 -> 552 -> 539 | Improved |
| replace DocNADE with one-hidden-layer DeepDocNADE | DocNADE · 20 Newsgroups (50 topics) | test perplexity per word: 896 -> 835 | Improved |
| replace DocNADE with one-hidden-layer DeepDocNADE | DocNADE · RCV1-V2 (50 topics) | test perplexity per word: 742 -> 579 | Improved |
| increase number of word-ordering ensembles M (ablation) | DeepDocNADE · 20 Newsgroups and RCV1-V2 | test perplexity per word | No clear effect |
| add DocNADE context component to feed-forward language model (ablation) | FFN · APNews language modeling (100 topics) | test perplexity per word: 119.78 -> 111.93 | Improved |
| increase number of grouped sentences per document from 1 to 5 (ablation) | DocNADE-LM · APNews language modeling (100 topics) | test perplexity per word: 111.93 -> 109.22 | Improved |
Closest papers by meaning
- Neural Autoregressive Distribution Estimation (JMLR 2016 · similarity 0.87)
- Document Informed Neural Autoregressive Topic Models with Distributional Prior (AAAI 2019 · similarity 0.87)
- A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data (TPAMI 2016 · similarity 0.87)
- textTOvec: DEEP CONTEXTUALIZED NEURAL AUTOREGRESSIVE TOPIC MODELS OF LANGUAGE WITH DISTRIBUTED COMPOSITIONAL PRIOR (ICLR 2019 · similarity 0.85)
- Generative Text Convolutional Neural Network for Hierarchical Document Representation Learning (TPAMI 2022 · similarity 0.83)
- A Discrete Variational Recurrent Topic Model without the Reparametrization Trick (NeurIPS 2020 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
