mlsanityData to 7 Oct 2026

Simulating Action Dynamics with Neural Process Networks

arXiv 1711.05313 ↗First posted 14 Nov 2017cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

Understanding procedural language requires anticipating the causal effects of actions, even when they are not explicitly stated. In this work, we introduce Neural Process Networks to understand procedural text through (neural) simulation of action dynamics. Our model complements existing memory architectures with dynamic entity tracking by explicitly modeling actions as state transformers. The model updates the states of the entities by executing learned action operators. Empirical results demonstrate that our proposed model can reason about the unstated causal effects of actions, allowing it to provide more accurate contextual information for understanding and generating procedural text, all while offering more interpretable internal representations than existing alternatives.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 17; 2023: 12; 2024: 8; 2025: 1; 2026: 3.

53 papers.

Sort:

By area:

  1. 2023Entity Tracking in Language Modelscited by 44
  2. 2023Causal Reasoning of Entities and Events in Procedural Textscited by 23
  3. 2021Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Eventscited by 22
  4. 2022Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processescited by 22
  5. 2021proScript: Partially Ordered Scripts Generation via Pre-trained Language Modelscited by 21
  6. 2021Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understandingcited by 19
  7. 2021Process-Level Representation of Scientific Protocols with Interactive Annotationcited by 16
  8. 2021SHARE: a System for Hierarchical Assistive Recipe Editingcited by 15
  9. 2022Coalescing Global and Local Information for Procedural Text Understandingcited by 10
  10. 2024CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Planscited by 10
  11. 2024Text2TimeSeries: Enhancing Financial Forecasting through Time Series Prediction Updates with Event-Driven Insights from Large Language Modelscited by 9
  12. 2022Reasoning about Procedures with Natural Language Processing: A Tutorialcited by 8
38 more
  1. 2022Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flowscited by 8
  2. 2023Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Trackingcited by 8
  3. 2023OpenPI2.0: An Improved Dataset for Entity Tracking in Textscited by 8
  4. 2023Localizing Active Objects from Egocentric Vision with Symbolic World Knowledgecited by 8
  5. 2022EvEntS ReaLM: Event Reasoning of Entity States via Language Modelscited by 7
  6. 2021Hallmarks of Human-Machine Collaboration: A framework for assessment in the DARPA Communicating with Computers Programcited by 6
  7. 2022LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-trainingcited by 5
  8. 2022Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenariocited by 5
  9. 2022Plug-and-Play Recipe Generation with Content Planningcited by 5
  10. 2023Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customizationcited by 5
  11. 2021SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domaincited by 4
  12. 2022Learning Action Conditions from Instructional Manuals for Instruction Understandingcited by 4
  13. 2022PASTA: A Dataset for Modeling Participant States in Narrativescited by 4
  14. 2023The Role of Semantic Parsing in Understanding Procedural Textcited by 4
  15. 2024MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actionscited by 4
  16. 2021Latent Alignment of Procedural Concepts in Multimodal Recipescited by 2
  17. 2021Tracking entities in technical procedures -- a new dataset and baselinescited by 2
  18. 2022Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehensioncited by 2
  19. 2022Assistive Recipe Editing through Critiquingcited by 2
  20. 2022Recipe Generation from Unsegmented Cooking Videoscited by 2
  21. 2023Transferring Procedural Knowledge across Commonsense Taskscited by 2
  22. 2024PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipescited by 2
  23. 2024Order-Based Pre-training Strategies for Procedural Text Understandingcited by 2
  24. 2025Stick to Facts: Towards Fidelity-oriented Product Description Generationcited by 2
  25. 2021Modeling Human Mental States with an Entity-based Narrative Graphcited by 1
  26. 2021Designing Multimodal Datasets for NLP Challengescited by 1
  27. 2021A Neural Edge-Editing Approach for Document-Level Relation Graph Extractioncited by 1
  28. 2022Procedural Text Understanding via Scene-Wise Evolutioncited by 1
  29. 2022Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decodingcited by 1
  30. 202250 Ways to Bake a Cookie: Mapping the Landscape of Procedural Textscited by 1
  31. 2023OpenPI-C: A Better Benchmark and Stronger Baseline for Open-Vocabulary State Trackingcited by 1
  32. 2023Implicit Affordance Acquisition via Causal Action-Effect Modeling in the Video Domaincited by 1
  33. 2024Consistent Joint Decision-Making with Heterogeneous Learning Modelscited by 1
  34. 2022TRAC: A Textual Benchmark for Reasoning about Actions and Changecited by 0
  35. 2023Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manualscited by 0
  36. 2023CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Textcited by 0
  37. 2024Unsupervised Learning of Graph from Recipescited by 0
  38. 2024Structured Event Reasoning with Large Language Modelscited by 0

50 most cited of 53 All 53 (JSON)