mlsanityData to 7 Oct 2026

Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers

arXiv 2103.16289 ↗First posted 30 Mar 2021cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potentially facilitate a dialogue system to produce knowledge grounded responses. However, integrating KGs into the dialogue generation process in an end-to-end manner is a non-trivial task. This paper proposes a novel architecture for integrating KGs into the response generation process by training a BERT model that learns to answer using the elements of the KG (entities and relations) in a multi-task, end-to-end setting. The k-hop subgraph of the KG is incorporated into the model during training and inference using Graph Laplacian. Empirical evaluation suggests that the model achieves better knowledge groundedness (measured via Entity F1 score) compared to other state-of-the-art models for both goal and non-goal oriented dialogues.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

29 of 41 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  6. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  7. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  8. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  9. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  10. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  11. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  12. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
17 more
  1. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  2. 2016Learning End-to-End Goal-Oriented Dialogcited by 104
  3. 2018Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systemscited by 70
  4. 2017Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generationcited by 61
  5. 2019Global-to-local Memory Pointer Networks for Task-Oriented Dialoguecited by 47
  6. 2017Improved Neural Relation Detection for Knowledge Base Question Answeringcited by 44
  7. 2016Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Accesscited by 36
  8. 2018SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approachcited by 18
  9. 2019Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphscited by 15
  10. 2020Hierarchical Transformer for Task Oriented Dialog Systemscited by 14
  11. 2017Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networkscited by 12
  12. 2020Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisationcited by 9
  13. 2019Learning Representation Mapping for Relation Detection in Knowledge Base Question Answeringcited by 7
  14. 2018Multi-turn Dialogue Response Generation in an Adversarial Learning Frameworkcited by 6
  15. 2019Using a KG-Copy Network for Non-Goal Oriented Dialoguescited by 6
  16. 2018Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphscited by 5
  17. 2020Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-Task Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 3; 2024: 0; 2025: 1.

8 papers.

  1. 2022RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Groundingcited by 47
  2. 2022DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generationcited by 19
  3. 2023CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answeringcited by 10
  4. 2022RoMe: A Robust Metric for Evaluating Natural Language Generationcited by 6
  5. 2025Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learningcited by 5
  6. 2023From Data to Dialogue: Leveraging the Structure of Knowledge Graphs for Conversational Exploratory Searchcited by 3
  7. 2022Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systemscited by 1
  8. 2023Voice-Based Conversational Agents and Knowledge Graphs for Improving News Search in Assisted Livingcited by 1