Comments (2)
我们当时做这个的目的是把三元组形式的标记转换成二元组的标记,以加速训练效率。
我们的目标是给出所有成对出现在训练集里的样本 i 和样本 j 的相似度 y_ij,并且 y_ij 需要满足:
- y_ij 在0~1之间
- y_ij 和 y_ik 需要满足原始训练集样本 i, j, k 组成的三元组指出的相似性关系,即y_ij >y_ik
只用以上条件作为约束求解y_ij ,得到的优化问题比较困难,为了让这个优化问题容易求解,我们又加了一个约束条件:
- y_ij 和未作fine-tuning的bert模型输出的样本 i, j 的相似度的 l2 距离尽可能小
这么做的想法是希望让得到的软标记 y_ij 对bert模型来说更加容易学习。
我们把以上约束条件加权转为无约束优化问题然后用l-bfgs算法求解,这样就估计出了样本i和样本j的相似度 。
from cail2019.
非常感谢大神的解惑
from cail2019.
Related Issues (12)
- 你好,我用你的程序,跑出来,评分只有0.52。感觉差太远了。我只把epoch设成1,batch_size设成8.其它没变。 HOT 30
- 关于Bert模型加载? HOT 11
- 关于模型数据预处理及模型输入的问题? HOT 1
- 数据label问题 HOT 5
- 启发式增广的代码有错误 HOT 1
- 问下官方公开的数据集是第几阶段的啊 HOT 1
- 作者您好!请问我该如何下载pytorch版本的BERT预训练模型呢?不胜感激! HOT 2
- 使用数据增广后报错 HOT 2
- from apex import FP16 rasied errors HOT 6
- Prediction Acc is 0.533 when running main.py and judger.py HOT 4
- 5fold and 1fold experiment GAP HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cail2019.