DeepAI AI Chat
Log In Sign Up

Unsupervised Label-aware Event Trigger and Argument Classification

by   Hongming Zhang, et al.

Identifying events and mapping them to pre-defined event types has long been an important natural language processing problem. Most previous work has been heavily relying on labor-intensive and domain-specific annotations while ignoring the semantic meaning contained in the labels of the event types. As a result, the learned models cannot effectively generalize to new domains, where new event types could be introduced. In this paper, we propose an unsupervised event extraction pipeline, which first identifies events with available tools (e.g., SRL) and then automatically maps them to pre-defined event types with our proposed unsupervised classification model. Rather than relying on annotated data, our model matches the semantics of identified events with those of event type labels. Specifically, we leverage pre-trained language models to contextually represent pre-defined types for both event triggers and arguments. After we map identified events to the target types via representation similarity, we use the event ontology (e.g., argument type "Victim" can only appear as the argument of event type "Attack") as global constraints to regularize the prediction. The proposed approach is shown to be very effective when tested on the ACE-2005 dataset, which has 33 trigger and 22 argument types. Without using any annotation, we successfully map 83 and 54 of previous zero-shot approaches.


page 1

page 2

page 3

page 4


Global Constraints with Prompting for Zero-Shot Event Argument Classification

Determining the role of event arguments is a crucial subtask of event ex...

Eliciting Knowledge from Language Models for Event Extraction

Eliciting knowledge contained in language models via prompt-based learni...

Semantic Pivoting Model for Effective Event Detection

Event Detection, which aims to identify and classify mentions of event i...

Event Extraction as Natural Language Generation

Event extraction (EE), the task that identifies event triggers and their...

COfEE: A Comprehensive Ontology for Event Extraction from text, with an online annotation tool

Data is published on the web over time in great volumes, but majority of...

Ontology-driven Event Type Classification in Images

Event classification can add valuable information for semantic search an...

Causal Intervention-based Prompt Debiasing for Event Argument Extraction

Prompt-based methods have become increasingly popular among information ...