# CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation

arXiv: https://arxiv.org/abs/2305.06294 · HTML: https://mlsanity.com/paper/2305.06294/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 27 of 27)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning](https://mlsanity.com/paper/2006.16779/) (2020)
- [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://mlsanity.com/paper/1911.02707/) (2019)
- [DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs](https://mlsanity.com/paper/1910.00610/) (2019)
- [GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2010.01447/) (2020)
- [Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking](https://mlsanity.com/paper/2104.04466/) (2021)
- [Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts](https://mlsanity.com/paper/2203.07285/) (2022)
- [Flexible End-to-End Dialogue System for Knowledge Grounded Conversation](https://mlsanity.com/paper/1709.04264/) (2017)
- [EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention](https://mlsanity.com/paper/2210.12463/) (2022)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [NGEP: A Graph-based Event Planning Framework for Story Generation](https://mlsanity.com/paper/2210.10602/) (2022)
- [Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition](https://mlsanity.com/paper/2004.10663/) (2020)
- [Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics](https://mlsanity.com/paper/2210.10618/) (2022)
- [Terminology-aware Medical Dialogue Generation](https://mlsanity.com/paper/2210.15551/) (2022)
- [Teach Me What to Say and I Will Learn What to Pick: Unsupervised Knowledge Selection Through Response Generation with Pretrained Generative Models](https://mlsanity.com/paper/2110.02067/) (2021)

## Built on by (most cited first, 8 of 8)

- [TwistList: Resources and Baselines for Tongue Twister Generation](https://mlsanity.com/paper/2306.03457/) (2023)
- [Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation](https://mlsanity.com/paper/2306.16195/) (2023)
- [Improving Biomedical Abstractive Summarisation with Knowledge Aggregation from Citation Papers](https://mlsanity.com/paper/2310.15684/) (2023)
- [RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models](https://mlsanity.com/paper/2401.09432/) (2023)
- [Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy](https://mlsanity.com/paper/2411.06723/) (2024)
- [A Cross-Attention Augmented Model for Event-Triggered Context-Aware Story Generation](https://mlsanity.com/paper/2311.11271/) (2023)
- [ACL Anthology Helper: A Tool to Retrieve and Manage Literature from ACL Anthology](https://mlsanity.com/paper/2310.20467/) (2023)
- [SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling](https://mlsanity.com/paper/2604.26630/) (2026)

## Abstract (arXiv)

Commonsense knowledge is crucial to many natural language processing tasks. Existing works usually incorporate graph knowledge with conventional graph neural networks (GNNs), resulting in a sequential pipeline that compartmentalizes the encoding processes for textual and graph-based knowledge. This compartmentalization does, however, not fully exploit the contextual interplay between these two types of input knowledge. In this paper, a novel context-aware graph-attention model (Context-aware GAT) is proposed, designed to effectively assimilate global features from relevant knowledge graphs through a context-enhanced knowledge aggregation mechanism. Specifically, the proposed framework employs an innovative approach to representation learning that harmonizes heterogeneous features by amalgamating flattened graph knowledge with text data. The hierarchical application of graph knowledge aggregation within connected subgraphs, complemented by contextual information, to bolster the generation of commonsense-driven dialogues is analyzed. Empirical results demonstrate that our framework outperforms conventional GNN-based language models in terms of performance. Both, automated and human evaluations affirm the significant performance enhancements achieved by our proposed model over the concept flow baseline.