Abstract
Event detection (ED), detecting events with specified types observed in given texts, is critical to many downstream applications. Existing ED methods generally require high-quality triggers annotated by human experts, which is labor-intensive, especially for those nontrivial texts about breaking events. In this paper, we propose a novel trigger-free ED framework that detects multiple events from a given text without pre-defined triggers. Specifically, we first shed light on the event correlations with input texts using a joint embedding paradigm. Next, we devise derangement-based contrastive learning to model fine-grained correlations between multi-event instances. Since events in training benchmarks are usually imbalanced, we further design a simple yet effective event derangement module for balanced training. Experimental results on two benchmarks show that our trigger-free method is remarkably competitive to state-of-the-art trigger-based baselines.
Original language | English |
---|---|
Title of host publication | ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Publisher | IEEE |
Pages | 10171-10175 |
Number of pages | 5 |
ISBN (Print) | 979-8-3503-4486-8 |
DOIs | |
Publication status | Published - 14 Apr 2024 |
Event | IEEE International Conference on Acoustics, Speech and Signal Processing: Signal Processing: The Foundation for True Intelligence - COEX, Seoul, Korea, Democratic People's Republic of Duration: 14 Apr 2024 → 19 Apr 2024 https://2024.ieeeicassp.org/ (conference website) https://2024.ieeeicassp.org/program-schedule/ (conference program) |
Publication series
Name | International Conference on Acoustics, Speech, and Signal Processing (ICASSP) |
---|---|
Publisher | IEEE |
Conference
Conference | IEEE International Conference on Acoustics, Speech and Signal Processing |
---|---|
Abbreviated title | ICASSP 2024 |
Country/Territory | Korea, Democratic People's Republic of |
City | Seoul |
Period | 14/04/24 → 19/04/24 |
Internet address |
|
User-Defined Keywords
- Event detection
- trigger-free paradigm
- multi-event correlations
- balanced training