mlsanityData to 14 Oct 2026

Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

arXiv 1704.07130 ↗First posted 24 Apr 2017cs.CLcited by 59

Not on the map. Why?

Abstract (arXiv)

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 16; 2022: 9; 2023: 14; 2024: 11; 2025: 5; 2026: 3.

59 papers.

Sort:

By area:

  1. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 367
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 75
  4. 2021CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systemscited by 62
  5. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  6. 2021Towards Knowledge-Grounded Counter Narrative Generation for Hate Speechcited by 42
  7. 2020Learning Rewards from Linguistic Feedbackcited by 41
  8. 2021Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Conceptscited by 37
  9. 2021ValueNet: A New Dataset for Human Value Driven Dialogue Systemcited by 34
  10. 2021Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completioncited by 32
  11. 2023Decision-Oriented Dialogue for Human-AI Collaborationcited by 29
  12. 2021DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Networkcited by 19
38 more
  1. 2021Improving Hyper-Relational Knowledge Graph Completioncited by 18
  2. 2022Geometry Interaction Knowledge Graph Embeddingscited by 18
  3. 2022Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policycited by 17
  4. 2021Reference-Centric Models for Grounded Collaborative Dialoguecited by 15
  5. 2022HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoningcited by 11
  6. 2021Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysiscited by 10
  7. 2021Maintaining Common Ground in Dynamic Environmentscited by 9
  8. 2021Analysis of Language Change in Collaborative Instruction Followingcited by 9
  9. 2024Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks Worldcited by 9
  10. 2025Measuring How (Not Just Whether) VLMs Build Common Groundcited by 8
  11. 2026MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Gamescited by 8
  12. 2022Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspectivecited by 7
  13. 2023Asking More Informative Questions for Grounded Retrievalcited by 6
  14. 2024Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communicationcited by 6
  15. 2022SPE: Symmetrical Prompt Enhancement for Fact Probingcited by 5
  16. 2023Symbolic Planning and Code Generation for Grounded Dialoguecited by 5
  17. 2024Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learningcited by 4
  18. 2024Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimizationcited by 4
  19. 2023Knowledge Graph Embedding with 3D Compound Geometric Transformationscited by 3
  20. 2023Towards a Neural Era in Dialogue Management for Collaboration: A Literature Surveycited by 3
  21. 2024Knowledge Graph Reasoning with Self-supervised Reinforcement Learningcited by 3
  22. 2025Characterizing Language Use in a Collaborative Situated Gamecited by 3
  23. 2021The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialoguescited by 2
  24. 2021Conversational AI Systems for Social Good: Opportunities and Challengescited by 2
  25. 2023Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorizationcited by 2
  26. 2023Adapting Knowledge for Few-shot Table-to-Text Generationcited by 2
  27. 2023Agreement Tracking for Multi-Issue Negotiation Dialoguescited by 2
  28. 2024Uncertainty-Aware Relational Graph Neural Network for Few-Shot Knowledge Graph Completioncited by 2
  29. 2024Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Explorationcited by 2
  30. 2025Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialogcited by 2
  31. 2025BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Actscited by 2
  32. 2022Do You Know My Emotion? Emotion-Aware Strategy Recognition towards a Persuasive Dialogue Systemcited by 1
  33. 2022Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systemscited by 1
  34. 2023FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completioncited by 1
  35. 2023MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generationcited by 1
  36. 2021A Neural Conversation Generation Model via Equivalent Shared Memory Investigationcited by 0
  37. 2022Towards Collaborative Question Answering: A Preliminary Studycited by 0
  38. 2022Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scenecited by 0

50 most cited of 59 All 59 (JSON)