当前位置:网站首页>ACL 2022 | small sample ner of sequence annotation: dual tower Bert model integrating tag semantics
ACL 2022 | small sample ner of sequence annotation: dual tower Bert model integrating tag semantics
2022-07-06 22:45:00 【Zhiyuan community】
Paper title :
Label Semantics for Few Shot Named Entity Recognition
https://arxiv.org/pdf/2203.08985.pdf
This is an article from ACL 2022 The article , The general idea is meta-learning On the basis of , Adopt double towers BERT The model is used to match the text characters and the corresponding label Encoding , And carry out the two Dot Product( Point multiplication ) Get the output to do a classification . The article is not complicated on the whole , There are few formulas involved , It is easy to understand the author's ideas . For serial annotation NER It's a good idea .
边栏推荐
猜你喜欢
View
Advantages of link local address in IPv6
NPDP认证|产品经理如何跨职能/跨团队沟通?
动作捕捉用于蛇运动分析及蛇形机器人开发
Traversal of a tree in first order, middle order, and then order
机试刷题1
Installation and use of labelimg
On the problems of born charge and non analytical correction in phonon and heat transport calculations
新手程序员该不该背代码?
Improving Multimodal Accuracy Through Modality Pre-training and Attention
随机推荐
Web APIs DOM 时间对象
NPDP certification | how do product managers communicate across functions / teams?
【雅思口语】安娜口语学习记录part1
Aardio - construct a multi button component with customplus library +plus
空结构体多大?
Adavit -- dynamic network with adaptive selection of computing structure
[untitled]
软考高级(信息系统项目管理师)高频考点:项目质量管理
柔性数组到底如何使用呢?
Jafka来源分析——Processor
Void keyword
Signed and unsigned keywords
Extern keyword
Leetcode: interview question 17.24 Maximum cumulative sum of submatrix (to be studied)
Return keyword
MySQL约束的分类、作用及用法
Sword finger offer question brushing record 1
The difference between enumeration and define macro
Should novice programmers memorize code?
Machine test question 1