《万字长文:浅谈多任务学习》侧重NLP和推荐系统,MLT

原文链接:https://mp.weixin.qq.com/s/iYQkwCs1xz2QIjRkg5nerg

Retrieve, Rerank, Read, then Iterate: Answering Open-Domain Questions of Arbitrary Complexity from Text
Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations
Recommending what video to watch next: a multitask ranking system
MMOE:Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
An Overview of Multi-Task Learning in Deep Neural Networks

A Frustratingly Easy Approach for Joint Entity and Relation Extraction
Multi-Task Deep Neural Networks for Natural Language Understanding
ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding

feature engineering之外的另一大神器!辅助任务enginering!

字节跳动内推

找我内推: 字节跳动各种岗位
作者: ZH奶酪(张贺)
邮箱: cheesezh@qq.com
出处: http://www.cnblogs.com/CheeseZH/
* 本文版权归作者和博客园共有,欢迎转载,但未经作者同意必须保留此段声明,且在文章页面明显位置给出原文连接,否则保留追究法律责任的权利。

原文地址:https://www.cnblogs.com/CheeseZH/p/14528149.html