mlsanityData to 7 Oct 2026

Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation

arXiv 1804.08069 ↗First posted 22 Apr 2018cs.CL cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders humans from understanding its generation process. We present an unsupervised discrete sentence representation learning method that can integrate with any existing encoder-decoder dialog models for interpretable response generation. Building upon variational autoencoders (VAEs), we present two novel models, DI-VAE and DI-VST that improve VAEs and can discover interpretable semantics via either auto encoding or context predicting. Our methods have been validated on real-world dialog datasets to discover semantic representations and enhance encoder-decoder models with interpretable generation.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 9; 2023: 6; 2024: 3; 2025: 1; 2026: 3.

34 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  4. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  5. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  6. 2022DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generationcited by 35
  7. 2021SKID RAW: Skill Discovery from Raw Trajectoriescited by 22
  8. 2021Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classificationcited by 14
  9. 2021DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformercited by 14
  10. 2021Truth-Conditional Captioning of Time Series Datacited by 11
  11. 2021MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Datacited by 9
  12. 2022EmpHi: Generating Empathetic Responses with Human-like Intentscited by 9
22 more
  1. 2024Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Expertscited by 9
  2. 2023Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Networkcited by 7
  3. 2024Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commentingcited by 7
  4. 2025Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codescited by 7
  5. 2022PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanismcited by 6
  6. 2023Learning Gaussian Mixture Representations for Tensor Time Series Forecastingcited by 6
  7. 2024Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logiccited by 5
  8. 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
  9. 2022Hidden Schema Networkscited by 4
  10. 2022Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representationcited by 4
  11. 2026Large Language Model as Token Compressor and Decompressorcited by 4
  12. 2021Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generationcited by 3
  13. 2022Data Augmentation for Intent Classificationcited by 3
  14. 2022Learning Interpretable Latent Dialogue Actions With Less Supervisioncited by 3
  15. 2021When is it permissible for artificial intelligence to lie? A trust-based approachcited by 2
  16. 2023Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Gamescited by 2
  17. 2021Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structurecited by 1
  18. 2026EXCODER: EXplainable Classification Of DiscretE time series Representationscited by 1
  19. 2021Domain Adaptation in Dialogue Systems using Transfer and Meta-Learningcited by 0
  20. 2023Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generationcited by 0
  21. 2023Topic-Guided Self-Introduction Generation for Social Media Userscited by 0
  22. 2026Entropic Auto-Encoding via Implicit Free-Energy Minimizationcited by 0