Few-shot Incremental Event Detection

• DOI: 10.1145/3634747
• Publication Date: 2023-12-02T12:10:35Z
• Authors: Hao Wang; Hanwen Shi; Jianyong Duan
• Keywords: Benchmark (surveying); Retraining; Complex Event Processing; Training set

Event detection tasks can enable the quick of events from texts and provide powerful support for downstream natural language processing tasks. Most such methods only detect a fixed set predefined event classes. To extend them to new class without losing ability old classes requires costly retraining model scratch. Incremental learning effectively solve this problem, but it abundant data In practice, however, lack high-quality labeled makes difficult obtain enough training. address above mentioned issues, we define task, few-shot incremental detection, which focuses on with limited data, while retaining extent possible. We created benchmark dataset IFSED task based FewEvent propose two benchmarks, IFSED-K IFSED-KP. Experimental results show that our approach has higher F1-score than baseline is more stable.