Wei Hu, Xinyi Wang, Zitao Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 longtailed 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. * Corresponding author My uncle died a year before I got married. Die NA Previous "Die" Data My uncle died a year before I got married. Marry New "Marry" Data NA Previous Model Current Model
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.15470")
get_code_for_paper("2310.15470")
have("2310.15470")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2310.15470.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2310.15470)
Connect an agent — have() is free.