mlsanityData to 14 Oct 2026

Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection

arXiv 2204.07275 ↗First posted 15 Apr 2022cs.CL cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types. One critical challenge is that the model would catastrophically forget old types when continually trained on new data. In this paper, we introduce Episodic Memory Prompts (EMP) to explicitly preserve the learned task-specific knowledge. Our method adopts continuous prompt for each task and they are optimized to instruct the model prediction and learn event-specific representation. The EMPs learned in previous tasks are carried along with the model in subsequent tasks, and can serve as a memory module that keeps the old knowledge and transferring to new tasks. Experiment results demonstrate the effectiveness of our method. Furthermore, we also conduct a comprehensive analysis of the new and old event types in lifelong learning.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 31 of its 54 references that are in the map. First posted on arXiv 15 Apr 2022.

Builds on

31 of 54 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2016Learning without Forgettingcited by 2,496
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  10. 2019How Can We Know What Language Models Know?cited by 959
  11. 2021Learning to Prompt for Continual Learningcited by 944
  12. 2019Large Scale Incremental Learningcited by 732
19 more
  1. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 689
  2. 2018End-to-End Incremental Learningcited by 597
  3. 2019Gradient based sample selection for online continual learningcited by 571
  4. 2021WARP: Word-level Adversarial ReProgrammingcited by 221
  5. 2019Episodic Memory in Lifelong Language Learningcited by 188
  6. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  7. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  8. 2020MAVEN: A Massive General Domain Event Detection Datasetcited by 104
  9. 2021LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5cited by 104
  10. 2020Continual Learning in Task-Oriented Dialogue Systemscited by 83
  11. 2019Sentence Embedding Alignment for Lifelong Relation Extractioncited by 70
  12. 2021Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Taskscited by 46
  13. 2022Continual Prompt Tuning for Dialog State Trackingcited by 44
  14. 2020Lifelong Language Knowledge Distillationcited by 31
  15. 2021CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Taskscited by 29
  16. 2022Consistent Representation Learning for Continual Relation Extractioncited by 28
  17. 2021Query and Extract: Refining Event Extraction as Type-oriented Binary Decodingcited by 26
  18. 2022The Art of Prompting: Event Detection based on Type Specific Promptscited by 9
  19. 2022Hierarchical Inductive Transfer for Continual Dialogue Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 9; 2025: 2; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  3. 2024Continual Learning with Pre-Trained Models: A Surveycited by 154
  4. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 64
  5. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  6. 2023X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspectscited by 28
  7. 2023The Devil is in the Details: On the Pitfalls of Event Extraction Evaluationcited by 19
  8. 2023On the Evolution of Knowledge Graphs: A Survey and Perspectivecited by 10
  9. 2023Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extractioncited by 9
  10. 2024Continual Learning for Smart City: A Surveycited by 9
  11. 2022An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understandingcited by 5
  12. 2023Continual Event Extraction with Semantic Confusion Rectificationcited by 5
11 more
  1. 2023Schema-adaptable Knowledge Graph Constructioncited by 4
  2. 2026Navigating Ideation Space: Decomposed Conceptual Representations for Positioning Scientific Ideascited by 4
  3. 2023Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understandingcited by 3
  4. 2024Continual Few-shot Event Detection via Hierarchical Augmentation Networkscited by 3
  5. 2024Lifelong Event Detection with Embedding Space Separation and Compactioncited by 2
  6. 2024Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Needcited by 2
  7. 2024Lifelong Event Detection via Optimal Transportcited by 2
  8. 2024Double Mixture: Towards Continual Event Detection from Speechcited by 1
  9. 2024Class-Incremental Few-Shot Event Detectioncited by 0
  10. 2025LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detectioncited by 0
  11. 2026The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligencecited by 0