本文主要是介绍The Art of Prompting: Event Detection based on Type Specific Prompts,对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!
Motivation
- 之前的研究表明prompt可以提高模型在事件检测方面的性能,包括
- 使用特定structure
- 使用每种事件类型特定的query
- 原型 trigger
- 这些尝试启发对不同prompt效果的探究
Settings
作者在3种setting下做了实验:
- Supervised event detection
- Few-shot Event detection
- 两个数据集\(D_{base}, D_{novel}\),前者规模大,后者小。后者用来作为第二个域。
- Zero-shot Event detection
- 只用第二个域的数据作为测试,不在\(D_{novel}\)上面fine-tune
Event Type Prompts
- Event Type Name
- Definition
- 如 Attack:violent or physical act causing harm or damage
- Prototype Seed Triggers
- 在判断事件类别\(T\)时,选取\(K\)个trigger word,他们作为\(T\)的触发词的次数占他们出现总次数的比例最大,并连接起来。
- Event Type Structure
- Continuous Soft Prompt
- 参考经典论文 Prefifix-tuning: Optimizing continuous prompts for generation
- APEX Prompt
- 综合prompt,包含:event type name, seed triggers, and definition
- 如下图所示
A Unified Framework for Event Detection
Experiments
Method |
Supervised ED |
Few-shot ED |
Zero-shot ED |
State of the art |
73.3 |
35.2 |
49.1 |
(a) Event Type name |
72.2 |
52.7 |
49.8 |
(b) Defifinition |
73.1 |
46.7 |
45.5 |
(c) Seed Triggers |
73.7 |
53.8 |
52.4 |
(d) Event Type Structure |
72.8 |
50.4 |
48.0 |
(e) Continuous Soft Prompt |
68.1 |
48.2 |
- |
Majority Voting of (a)-(e) |
73.9 |
52.1 |
48.7 |
(f) APEX Prompt |
74.9 |
57.4 |
55.3 |
这篇关于The Art of Prompting: Event Detection based on Type Specific Prompts的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!