Research map / Image generation / GANs
Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Train with query-response-future-turn triples and both forward and backward generative discriminators | Posterior-GAN · DailyDialog | Dist-2: 0.3088 -> 0.3549 | Helped |
| Train with query-response-future-turn triples and both forward and backward generative discriminators | Posterior-GAN · OpenSubtitles (OSDb) | BLEU: 0.1756 -> 0.1955 | Helped |
| Use the forward discriminator alone instead of both discriminators (ablation) | Posterior-GAN · DailyDialog | Dist-2: 0.2950 -> 0.2995 | Helped |
| Use the forward discriminator alone instead of both discriminators (ablation) | Posterior-GAN · OpenSubtitles (OSDb) | Dist-2: 0.0180 -> 0.0170 | No clear effect |
| Use the backward discriminator alone instead of both discriminators (ablation) | Posterior-GAN · DailyDialog | BLEU: 0.2183 -> 0.2130 | No clear effect |
| Use the backward discriminator alone instead of both discriminators (ablation) | Posterior-GAN · OpenSubtitles (OSDb) | BLEU: 0.1955 -> 0.1756 | No clear effect |
| Combine forward and backward generative discriminators rather than using either alone (ablation) | Posterior-GAN · DailyDialog | BLEU: 0.2130 -> 0.2183 | Helped |
| Combine forward and backward generative discriminators rather than using either alone (ablation) | Posterior-GAN · OpenSubtitles (OSDb) | Average: 0.6217 -> 0.6346 | Helped |
Closest papers by meaning
- Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning (CVPR 2018 · similarity 0.91)
- Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (AAAI 2016 · similarity 0.89)
- A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues (AAAI 2017 · similarity 0.88)
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization (NeurIPS 2018 · similarity 0.88)
- Mechanism-Aware Neural Machine for Dialogue Response Generation (AAAI 2017 · similarity 0.87)
- DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder (ICLR 2019 · similarity 0.87)
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.