mlsanityData to 7 Oct 2026

Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning

arXiv 2205.01376 ↗First posted 3 May 2022cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Recent work has shown that NLP tasks such as Relation Extraction (RE) can be recasted as Textual Entailment tasks using verbalizations, with strong performance in zero-shot and few-shot settings thanks to pre-trained entailment models. The fact that relations in current RE datasets are easily verbalized casts doubts on whether entailment would be effective in more complex tasks. In this work we show that entailment is also effective in Event Argument Extraction (EAE), reducing the need of manual annotation to 50% and 20% in ACE and WikiEvents respectively, while achieving the same performance as with full training. More importantly, we show that recasting EAE as entailment alleviates the dependency on schemas, which has been a road-block for transferring annotations between domains. Thanks to the entailment, the multi-source transfer between ACE and WikiEvents further reduces annotation down to 10% and 5% (respectively) of the full training without transfer. Our analysis shows that the key to good results is the use of several entailment datasets to pre-train the entailment model. Similar to previous approaches, our method requires a small amount of effort for manual verbalization: only less than 15 minutes per event argument type is needed, and comparable results can be achieved with users with different level of expertise.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 50 of its 72 references that are in the map. First posted on arXiv 3 May 2022.

Builds on

50 of 72 references.

References · 50

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  9. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  10. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  11. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  12. 2015A large annotated corpus for learning natural language inferencecited by 1,837
38 more
  1. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  2. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  3. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  4. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  5. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  6. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  7. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  8. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  9. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  10. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  11. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  12. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  13. 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 299
  14. 2018Hypothesis Only Baselines in Natural Language Inferencecited by 291
  15. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 271
  16. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  17. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
  18. 2021How Many Data Points is a Prompt Worth?cited by 197
  19. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
  20. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 173
  21. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  22. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  23. 2018Breaking NLI Systems with Sentences that Require Simple Lexical Inferencescited by 134
  24. 2021Entailment as Few-Shot Learnercited by 122
  25. 2018Transforming Question Answering Datasets Into Natural Language Inference Datasetscited by 99
  26. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  27. 2019Multi-Sentence Argument Linkingcited by 80
  28. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 80
  29. 2021Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extractioncited by 73
  30. 2018Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailmentcited by 58
  31. 2018Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learningcited by 52
  32. 2020Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Startcited by 44
  33. 2021The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Predictioncited by 39
  34. 2020Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encodingcited by 28
  35. 2019Reading the Manual: Event Extraction as Definition Comprehensioncited by 26
  36. 2021Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Modelscited by 13
  37. 2020Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extractioncited by 11
  38. 2022ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizationscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 10; 2025: 2; 2026: 1.

25 papers.

Sort:

By area:

  1. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  2. 2023GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extractioncited by 116
  3. 2023Universal Information Extraction as Unified Semantic Matchingcited by 47
  4. 2023Large Language Model Instruction Following: A Survey of Progresses and Challengescited by 31
  5. 2023TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extractioncited by 27
  6. 2022GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Rolescited by 25
  7. 2023The Devil is in the Details: On the Pitfalls of Event Extraction Evaluationcited by 18
  8. 2023What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventoriescited by 9
  9. 2022OpenStance: Real-world Zero-shot Stance Detectioncited by 7
  10. 2024Improving Event Definition Following For Zero-Shot Event Detectioncited by 7
  11. 2023STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Modelscited by 6
  12. 2024Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extractioncited by 5
13 more
  1. 2022Learning to Select from Multiple Optionscited by 4
  2. 2023Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detectioncited by 4
  3. 2024Explicating the Implicit: Argument Detection Beyond Sentence Boundariescited by 4
  4. 2024On the use of Silver Standard Data for Zero-shot Classification Tasks in Information Extractioncited by 3
  5. 2024Textual Entailment for Effective Triple Validation in Object Predictioncited by 2
  6. 2024Event Extraction in Basque: Typologically motivated Cross-Lingual Transfer-Learning Analysiscited by 2
  7. 2025MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphingcited by 2
  8. 2024X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classificationcited by 1
  9. 2024Asking and Answering Questions to Extract Event-Argument Structurescited by 1
  10. 2026Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extractioncited by 1
  11. 2024Entangled Relations: Leveraging NLI and Meta-analysis to Enhance Biomedical Relation Extractioncited by 0
  12. 2024Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction Taskscited by 0
  13. 2025Medical Argument Mining: Exploitation of Scarce Data Using NLI Systemscited by 0