事件抽取文献整理(2018)

前言

之前研究事件抽取领域(NLP一个小领域信息抽取的子领域), 之前整理过一些文献。

本文是 事件抽取文献整理(2019) 的后续。

事件抽取文献整理(2020-2021)
+
事件抽取文献整理(2019)
+
事件抽取文献整理(2018)
+
事件抽取文献整理(2008-2017)

模型标题后有$代表有给代码

论文

### DCFEE

DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data (aclanthology.org)
无官方源码, 不过有演示系统，前端界面可以参考
Document-level Chinese
中文

Financial event knowledge base

Zeng et al.

Scale Up Event Extraction Learning via Automatic Training Data Generation
无官方源码

Huang et al.

Zero-Shot Transfer Learning for Event Extraction (aclanthology.org)
代码 wilburOne/ZeroShotEvent (github.com)基于theno… 可能比较难看懂
AMR parse

DEEB-RNN

Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention (aclanthology.org)
无官方源码

只有event trigger
Hierarchical and Supervised Attention

SELF

Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection (aclanthology.org)
无官方源码
只有event trigger

DBRNN

Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction (AAAI)
无官方源码

JMEE $

Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation (aclanthology.org)
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation (arxiv.org)
arXiv版有源码链接: lx865712528/EMNLP2018-JMEE (github.com)

有BiLSTM(准确来说是DynamicLSTM, Long Short-Term Memory with Dynamic Skip Connections, 代码: Lin-Youth/DynamicLSTM(github.com))
GCN网络
Highway 层(不是普通的residual shortcut)
selfAttention层

Ferguson et al.
Semi-Supervised Event Extraction with Paraphrase Clusters (aclanthology.org)
论文中给的项目已经找不到

只给了触发词抽取(事件类型)的结果
本文用聚类的方式