Continual Event Extraction with Semantic Confusion Rectification
This addresses continual learning challenges in event extraction for NLP applications, though it appears incremental in method.
The paper tackles the problem of continual event extraction where models must extract emerging event information without forgetting previous knowledge, addressing semantic confusion from updated annotations and event type imbalance. Their model outperforms state-of-the-art baselines and shows proficiency on imbalanced datasets.
We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting. We observe that the semantic confusion on event types stems from the annotations of the same text being updated over time. The imbalance between event types even aggravates this issue. This paper proposes a novel continual event extraction model with semantic confusion rectification. We mark pseudo labels for each sentence to alleviate semantic confusion. We transfer pivotal knowledge between current and previous models to enhance the understanding of event types. Moreover, we encourage the model to focus on the semantics of long-tailed event types by leveraging other associated types. Experimental results show that our model outperforms state-of-the-art baselines and is proficient in imbalanced datasets.