.png){kind=icon}
返回
Span-based few-shot event detection via aligning external knowledge
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106327.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Few -shot Event Detection (FSED) aims to identify novel event types in new domains with very limited annotated data. Previous PN-based (Prototypical Network) joint methods suffer from insufficient learning of token -wise label dependency and inaccurate prototypes. To solve these problems, we propose a span -based FSED model, called SpanFSED, which decomposes FSED into two subprocesses, including span extractor and event classifier. In span extraction, we convert sequential labels into a global boundary matrix that enables the span extractor to acquire precise boundary information irrespective of label dependency. In event classification, we align event types with an outside knowledge base like FrameNet and construct an enhanced support set, which injects more trigger information into the prototypical network of event prototypes. The superior performance of SpanFSED is demonstrated through extensive experiments on four event detection datasets, i.e., ACE2005, ERE, MAVEN and FewEvent. Access to our code and data is facilitated through the following link: https://github.com/rickltt/FewShot_ED.
Keyword:
Few-shot event detection
Prototypical network
External knowledge base
Global boundary matrix
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.0W
机构
引用论文
Kinematic analysis of limb movements in neuropsychological research: Subtle deficits and recovery of function.神经心理学研究中肢体运动的运动学分析: 细微的缺陷和功能的恢复。
.png){kind=icon}
PREAI
分享收藏
FOXO3 protects nucleus pulposus cells against apoptosis under nutrient deficiency via autophagy
PREAI
分享收藏Treatment of variable valence in organic nomenclature (lambda convention) (Recommendations 1983)
OAAI
OAAI分享收藏
查看更多内容