mlsanityData to 7 Oct 2026

Learning Interpretable Latent Dialogue Actions With Less Supervision

arXiv 2209.11128 ↗First posted 22 Sep 2022cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit annotation of semantic information. Unlike previous works, our approach models the system and user turns separately and performs database query modeling, which makes the model applicable to task-oriented dialogues while producing easily interpretable action latent variables. We show that our model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets, and we propose a way to measure dialogue success without the need for expert annotation. Finally, we propose a novel way to explain semantics of the latent variables with respect to system actions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 22 Sep 2022.

Builds on

35 of 47 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2015Generating Sentences from a Continuous Spacecited by 607
  9. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  10. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  11. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  12. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
23 more
  1. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  2. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  3. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  4. 2019Open Sesame: Getting Inside BERT's Linguistic Knowledgecited by 119
  5. 2016Learning End-to-End Goal-Oriented Dialogcited by 104
  6. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  7. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  8. 2019Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Modelscited by 53
  9. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  10. 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
  11. 2020Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialogcited by 37
  12. 2020Variational Transformers for Diverse Response Generationcited by 36
  13. 2018Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generationcited by 34
  14. 2020LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimizationcited by 30
  15. 2020Structured Attention for Unsupervised Dialogue Structure Inductioncited by 19
  16. 2021DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddingscited by 19
  17. 2019Unsupervised Dialog Structure Learningcited by 16
  18. 2017Latent Intention Dialogue Modelscited by 15
  19. 2016Unsupervised Dialogue Act Induction using Gaussian Mixturescited by 6
  20. 2020Unsupervised Learning of KB Queries in Task-Oriented Dialogscited by 6
  21. 2020An Investigation of Language Model Interpretability via Sentence Editingcited by 4
  22. 2018Quantized-Dialog Language Model for Goal-Oriented Conversational Systemscited by 2
  23. 2020Generalizable and Explainable Dialogue Generation via Explicit Action Learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logiccited by 5
  2. 2024Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channelcited by 5
  3. 2026MAPS: Modeling Co-Existing Subjective Perspectives and Shared Meaning in Multi-Agent Cognitive Dialoguecited by 0