# Document-Level Event Argument Extraction by Conditional Generation

arXiv: https://arxiv.org/abs/2104.05919 · HTML: https://mlsanity.com/paper/2104.05919/

## Key facts

- Cited by 155 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning](https://mlsanity.com/paper/1905.06549/) (2019)
- [Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network](https://mlsanity.com/paper/2006.05702/) (2020)
- [Multi-Sentence Argument Linking](https://mlsanity.com/paper/1911.03766/) (2019)
- [Zero-Shot Transfer Learning for Event Extraction](https://mlsanity.com/paper/1707.01066/) (2017)
- [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https://mlsanity.com/paper/1910.11621/) (2019)
- [Reading the Manual: Event Extraction as Definition Comprehension](https://mlsanity.com/paper/1912.01586/) (2019)
- [Extensively Matching for Few-shot Learning Event Detection](https://mlsanity.com/paper/2006.10093/) (2020)
- [Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction](https://mlsanity.com/paper/2010.11325/) (2020)

## Built on by (most cited first, 30 of 155)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [Unified Structure Generation for Universal Information Extraction](https://mlsanity.com/paper/2203.12277/) (2022)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models](https://mlsanity.com/paper/2310.20410/) (2023)
- [DEGREE: A Data-Efficient Generation-Based Event Extraction Model](https://mlsanity.com/paper/2108.12724/) (2021)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://mlsanity.com/paper/2210.12810/) (2022)
- [Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction](https://mlsanity.com/paper/2202.12109/) (2022)
- [Generative Knowledge Graph Construction: A Review](https://mlsanity.com/paper/2210.12714/) (2022)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction](https://mlsanity.com/paper/2203.08308/) (2022)
- [Dynamic Prefix-Tuning for Generative Template-based Event Extraction](https://mlsanity.com/paper/2205.06166/) (2022)
- [Document-level Entity-based Extraction as Template Generation](https://mlsanity.com/paper/2109.04901/) (2021)
- [ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning](https://mlsanity.com/paper/2104.08350/) (2021)
- [TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction](https://mlsanity.com/paper/2311.09562/) (2023)
- [GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles](https://mlsanity.com/paper/2205.12505/) (2022)
- [Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning](https://mlsanity.com/paper/2205.01376/) (2022)
- [ADELIE: Aligning Large Language Models on Information Extraction](https://mlsanity.com/paper/2405.05008/) (2024)
- [DICE: Data-Efficient Clinical Event Extraction with Generative Models](https://mlsanity.com/paper/2208.07989/) (2022)
- [Joint Multimedia Event Extraction from Video and Article](https://mlsanity.com/paper/2109.12776/) (2021)
- [ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification](https://mlsanity.com/paper/2204.07434/) (2022)
- [AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model](https://mlsanity.com/paper/2305.16734/) (2023)
- [The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation](https://mlsanity.com/paper/2306.06918/) (2023)
- [Corpus-based Open-Domain Event Type Induction](https://mlsanity.com/paper/2109.03322/) (2021)
- [Retrieval-Augmented Generative Question Answering for Event Argument Extraction](https://mlsanity.com/paper/2211.07067/) (2022)
- [Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines](https://mlsanity.com/paper/2502.16377/) (2025)

## Abstract (arXiv)

Event extraction has long been treated as a sentence-level task in the IE community. We argue that this setting does not match human information-seeking behavior and leads to incomplete and uninformative extraction results. We propose a document-level neural event argument extraction model by formulating the task as conditional generation following event templates. We also compile a new document-level event extraction benchmark dataset WikiEvents which includes complete event and coreference annotation. On the task of argument extraction, we achieve an absolute gain of 7.6% F1 and 5.7% F1 over the next best model on the RAMS and WikiEvents datasets respectively. On the more challenging task of informative argument extraction, which requires implicit coreference reasoning, we achieve a 9.3% F1 gain over the best baseline. To demonstrate the portability of our model, we also create the first end-to-end zero-shot event extraction framework and achieve 97% of fully supervised model's trigger extraction performance and 82% of the argument extraction performance given only access to 10 out of the 33 types on ACE.