atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Paraphrase Generation with Latent Bag of Words

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 34 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 changedWhereMeasuredEffect
Add a predicted latent BOW plan to guide decodingLSTM seq2seq · QuoraBLEU-4: 24.89 -> 26.17Helped
Add a predicted latent BOW plan to guide decodingLSTM seq2seq · MSCOCOBLEU-4: 23.66 -> 25.27Helped
Use the target BOW during generationLBOW · QuoraBLEU-4: 26.17 -> 49.47Helped
Use the target BOW during generationLBOW · MSCOCOBLEU-4: 25.27 -> 52.64Helped
Use Gumbel sampling instead of top-k selection for the BOW (ablation)LBOW · QuoraBLEU-4: 26.17 -> 26.14No clear effect
Use Gumbel sampling instead of top-k selection for the BOW (ablation)LBOW · MSCOCOBLEU-4: 25.27 -> 24.98No clear effect
Stop gradients from the decoder to the encoder (ablation)LBOW · QuoraBLEU-4: 26.17 -> 10.36Hurt
Stop gradients from the decoder to the encoder (ablation)LBOW · MSCOCOBLEU-4: 25.27 -> 9.28Hurt
Add target-BOW supervision to the latent BOW predictorLBOW · Quora and MSCOCOgeneration performanceHelped

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy