SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection
This addresses the need for more accurate and representative evaluation in ODED, which is crucial for researchers and practitioners working on event detection in diverse real-world scenarios, though it is incremental as it builds on existing evaluation challenges.
The paper tackles the problem of evaluating Open Domain Event Detection (ODED) methods, which suffer from limited benchmarks and token-level metrics that fail to capture semantic similarity, by proposing SEOE, a framework that constructs a scalable benchmark with 564 event types across 7 domains and uses LLMs to compute a semantic F1-score, validated through extensive experiments.
Automatic evaluation for Open Domain Event Detection (ODED) is a highly challenging task, because ODED is characterized by a vast diversity of un-constrained output labels from various domains. Nearly all existing evaluation methods for ODED usually first construct evaluation benchmarks with limited labels and domain coverage, and then evaluate ODED methods using metrics based on token-level label matching rules. However, this kind of evaluation framework faces two issues: (1) The limited evaluation benchmarks lack representatives of the real world, making it difficult to accurately reflect the performance of various ODED methods in real-world scenarios; (2) Evaluation metrics based on token-level matching rules fail to capture semantic similarity between predictions and golden labels. To address these two problems above, we propose a scalable and reliable Semantic-level Evaluation framework for Open domain Event detection (SEOE) by constructing a more representative evaluation benchmark and introducing a semantic evaluation metric. Specifically, our proposed framework first constructs a scalable evaluation benchmark that currently includes 564 event types covering 7 major domains, with a cost-effective supplementary annotation strategy to ensure the benchmark's representativeness. The strategy also allows for the supplement of new event types and domains in the future. Then, the proposed SEOE leverages large language models (LLMs) as automatic evaluation agents to compute a semantic F1-score, incorporating fine-grained definitions of semantically similar labels to enhance the reliability of the evaluation. Extensive experiments validate the representatives of the benchmark and the reliability of the semantic evaluation metric. Existing ODED methods are thoroughly evaluated, and the error patterns of predictions are analyzed, revealing several insightful findings.