# EventGraph: Event Extraction as Semantic Graph Parsing

arXiv: https://arxiv.org/abs/2210.08646 · HTML: https://mlsanity.com/paper/2210.08646/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 16 Oct 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Named Entity Recognition as Dependency Parsing](https://mlsanity.com/paper/2005.07150/) (2020)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation](https://mlsanity.com/paper/1809.09078/) (2018)
- [Joint Extraction of Events and Entities within a Document Context](https://mlsanity.com/paper/1609.03632/) (2016)
- [Simpler but More Accurate Semantic Dependency Parsing](https://mlsanity.com/paper/1807.01396/) (2018)
- [Dynamic Prefix-Tuning for Generative Template-based Event Extraction](https://mlsanity.com/paper/2205.06166/) (2022)
- [Structured Sentiment Analysis as Dependency Graph Parsing](https://mlsanity.com/paper/2105.14504/) (2021)
- [A Transition-Based Directed Acyclic Graph Parser for UCCA](https://mlsanity.com/paper/1704.00552/) (2017)
- ['UFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN](https://mlsanity.com/paper/2011.00758/) (2020)
- [Direct parsing to sentiment graphs](https://mlsanity.com/paper/2203.13209/) (2022)

## Built on by (most cited first, 4 of 4)

- [MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation](https://mlsanity.com/paper/2311.09105/) (2023)
- [Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2022): Workshop and Shared Task Report](https://mlsanity.com/paper/2211.11359/) (2022)
- [A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event Extraction](https://mlsanity.com/paper/2305.15051/) (2023)
- [JSEEGraph: Joint Structured Event Extraction as Graph Parsing](https://mlsanity.com/paper/2306.14633/) (2023)

## Abstract (arXiv)

Event extraction involves the detection and extraction of both the event triggers and corresponding event arguments. Existing systems often decompose event extraction into multiple subtasks, without considering their possible interactions. In this paper, we propose EventGraph, a joint framework for event extraction, which encodes events as graphs. We represent event triggers and arguments as nodes in a semantic graph. Event extraction therefore becomes a graph parsing problem, which provides the following advantages: 1) performing event detection and argument extraction jointly; 2) detecting and extracting multiple events from a piece of text; and 3) capturing the complicated interaction between event arguments and triggers. Experimental results on ACE2005 show that our model is competitive to state-of-the-art systems and has substantially improved the results on argument extraction. Additionally, we create two new datasets from ACE2005 where we keep the entire text spans for event arguments, instead of just the head word(s). Our code and models are released as open-source.