Event Extraction as Natural Language Generation

by   I-Hung Hsu, et al.

Event extraction (EE), the task that identifies event triggers and their arguments in text, is usually formulated as a classification or structured prediction problem. Such models usually reduce labels to numeric identifiers, making them unable to take advantage of label semantics (e.g. an event type named Arrest is related to words like arrest, detain, or apprehend). This prevents the generalization to new event types. In this work, we formulate EE as a natural language generation task and propose GenEE, a model that not only captures complex dependencies within an event but also generalizes well to unseen or rare event types. Given a passage and an event type, GenEE is trained to generate a natural sentence following a predefined template for that event type. The generated output is then decoded into trigger and argument predictions. The autoregressive generation process naturally models the dependencies among the predictions – each new word predicted depends on those already generated in the output sentence. Using carefully designed input prompts during generation, GenEE is able to capture label semantics, which enables the generalization to new event types. Empirical results show that our model achieves strong performance on event extraction tasks under all zero-shot, few-shot, and high-resource scenarios. Especially, in the high-resource setting, GenEE outperforms the state-of-the-art model on argument extraction and gets competitive results with the current best on end-to-end EE tasks.


page 1

page 2

page 3

page 4


Code4Struct: Code Generation for Few-Shot Structured Prediction from Natural Language

Large Language Model (LLM) trained on the mixture of text and code has d...

Dynamic Prefix-Tuning for Generative Template-based Event Extraction

We consider event extraction in a generative manner with template-based ...

Unsupervised Label-aware Event Trigger and Argument Classification

Identifying events and mapping them to pre-defined event types has long ...

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

We study the problem of event extraction from text data, which requires ...

Efficient Zero-shot Event Extraction with Context-Definition Alignment

Event extraction (EE) is the task of identifying interested event mentio...

AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model

Event argument extraction (EAE) identifies event arguments and their spe...

Extending Event Detection to New Types with Learning from Keywords

Traditional event detection classifies a word or a phrase in a given sen...

Please sign up or login with your details

Forgot password? Click here to reset