NLP/Event-Extraction
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
missQian 2020-11-16 00:38:26 +08:00 committed by GitHub
parent cb6a0c2136
commit 77a4058826
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@ -1244,6 +1244,23 @@ Keywords: Data Generation, Distant Supervision
### 阅读理解式事件抽取
#### 2020
<details/>
<summary/>
<a href="https://arxiv.org/abs/2004.13625">Event Extraction by Answering (Almost) Natural Questions, EMNLP 2020 </a> by <i> Xinya Du and Claire Cardie(<a href="https://github.com/xinyadu/eeqa">Github</a>)</summary><blockquote><p align="justify">
主要思想：事件提取问题需要检测事件触发并提取其相应的参数。
事件参数提取中的现有工作通常严重依赖于作为预处理/并发步骤的实体识别，这导致了众所周知的错误传播问题。
为了避免这个问题，我们引入了一种新的事件抽取范式，将其形式化为问答(QA)任务，该任务以端到端的方式提取事件论元。
实证结果表明，我们的框架优于现有的方法;
此外，它还能够提取训练时未见角色的事件论元。
![image](https://github.com/xiaoqian19940510/Event-Extraction/blob/master/figures/0.png)
数据集：ACE
</p></blockquote></details>
#### 2019
<details/>
<summary/>