mlsanityData to 14 Oct 2026

PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation

arXiv 2211.00910 ↗First posted 2 Nov 2022cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy. To this end, we introduce PLATO-K based on two-stage dialogic learning to strengthen internal knowledge memorization and external knowledge exploitation. In the first stage, PLATO-K learns through massive dialogue corpora and memorizes essential knowledge into model parameters. In the second stage, PLATO-K mimics human beings to search for external information and to leverage the knowledge in response generation. Extensive experiments reveal that the knowledge issue is alleviated significantly in PLATO-K with such comprehensive internal and external knowledge enhancement. Compared to the existing state-of-the-art Chinese dialogue model, the overall engagingness of PLATO-K is improved remarkably by 36.2% and 49.2% on chit-chat and knowledge-intensive conversations.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 39 references that are in the map. First posted on arXiv 2 Nov 2022.

Builds on

34 of 39 references.

References · 34

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  5. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  8. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  9. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  10. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  11. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  12. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
22 more
  1. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  2. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 670
  3. 2020Recipes for building an open-domain chatbotcited by 593
  4. 2020Towards a Human-like Open-Domain Chatbotcited by 470
  5. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  6. 2021ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 260
  7. 2021Internet-Augmented Dialogue Generationcited by 217
  8. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 198
  9. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 195
  10. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  11. 2020Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?cited by 127
  12. 2019ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisonscited by 83
  13. 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
  14. 2021Anticipating Safety Issues in E2E Conversational AI: Framework and Toolingcited by 78
  15. 2020A Large-Scale Chinese Short-Text Conversation Datasetcited by 77
  16. 2021ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 46
  17. 2021PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generationcited by 37
  18. 2021EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Trainingcited by 34
  19. 2021ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generationcited by 31
  20. 2022EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Trainingcited by 31
  21. 2022Towards Boosting the Open-Domain Chatbot with Human Feedbackcited by 11
  22. 2022Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledgecited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaborationcited by 11
  2. 2023GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generationcited by 9