mlsanityData to 7 Oct 2026

Generative Conversational Networks

arXiv 2106.08484 ↗First posted 15 Jun 2021cs.CL cs.HCcited by 11

Not on the map. Why?

Abstract (arXiv)

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent's performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 26 of its 32 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

26 of 32 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  4. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  5. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  6. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  7. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  8. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  9. 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 124
  10. 2019Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Datacited by 103
  11. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  12. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
14 more
  1. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  2. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  3. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  4. 2020Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representationscited by 42
  5. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  6. 2020Coach: A Coarse-to-Fine Approach for Cross-domain Slot Fillingcited by 38
  7. 2019Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systemscited by 25
  8. 2021Few Shot Dialogue State Tracking using Meta-learningcited by 16
  9. 2020C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Fillingcited by 11
  10. 2015Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systemscited by 9
  11. 2020Data Augmentation for Spoken Language Understanding via Pretrained Language Modelscited by 9
  12. 2021ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classificationcited by 8
  13. 2020Template Guided Text Generation for Task-Oriented Dialoguecited by 5
  14. 2018Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systemscited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 5; 2024: 0; 2025: 1.

11 papers.

  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  3. 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
  4. 2022Weakly Supervised Data Augmentation Through Prompting for Dialogue Understandingcited by 32
  5. 2022LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Taggingcited by 29
  6. 2023Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Informationcited by 24
  7. 2023NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violationcited by 24
  8. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingcited by 5
  9. 2022Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networkscited by 2
  10. 2021Training Conversational Agents with Generative Conversational Networkscited by 0
  11. 2025A Longitudinal Study on Different Annotator Feedback Loops in Complex RAG Taskscited by 0