当前位置:网站首页>Thesis reading_ ICD code_ MSMN
Thesis reading_ ICD code_ MSMN
2022-07-03 04:43:00 【xieyan0811】
Introduce
English title :Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding
Chinese title : Automatically ICD Encoded synonym matching network
Address of thesis :https://export.arxiv.org/pdf/2203.01515.pdf
field : natural language processing 、 Biomedical
Time of publication :2022
author :Zheng Yuan etc. , Tsinghua University , Alibaba
Source :ACL
Code and data : https://github.com/GanjinZero/ICD-MSMN
Reading time :2022.06.14
Journal entry
By substituting external resources UMLS, Papers collected Synonyms for each code , So as to make up for the electronic medical record and ICD The problem of different synonyms in coding description .
Its algorithm is not as sophisticated as some previous models , But after introducing external resources , The effect is indeed improved a lot .
extensive reading
- Aiming at problems :ICD One meaning multi word problem in coding
- The core approach :
- Put forward Multi synonym matching network (MSMN)
- Use LSTM+ Long attention
- Will encode synonyms As query Focus on different phrases in the description , So as to generate and ICD Coding related representations .
- Use Biaffine ICD code Text representation of similarity , For final classification .
- Understanding after extensive reading :
- After half an hour , Half an hour to tidy up ( This is a short passage )
Method
ICD Encoding synonyms
Use UMLS( Integrated medical language system ) Knowledge map , Yes ICD Code description for extension , First , Describe the code l1 And UMLS Concept unique identifier in CUIs alignment ; And then from UMLS The selections in have the same CUIs Synonyms of English terms , And by deleting hyphens and words “NOS” To add additional synonyms . To each of them ICD Code generation {l2,l3…lM} Text , The following is used N Indicates the number of words contained in each description .
code
Use LSTM As an encoder , Use the pre trained word vector to translate words wi mapping xi, Use d Two way of layer LSTM, Embed words as input , Calculate its hidden layer as a representation .
When encoding synonyms , Encode with the same encoder , Then get its representation with maximum pooling :
Multiple synonyms attention
Inspired by the attention of many heads , In this paper, we use Multiple synonyms attention , Cut the hidden layer into M block (M head ):
here , Use the expression of encoding synonyms qj To query Hj, use Hj and qj Linear transformation of Calculate attention score a; The relevant encoding of text and code synonyms is available Ha Get . Aggregate encoding based text representation v, When you only need to work with When a code matches , Use
classifier
The classifier is used to judge the text S Does it include ICD code l, Based on the previously calculated dependency coding The text means vl and Coded representation qj, Use double affine transformation to measure the similarity of classification .
Before, many models only relied on coding , Therefore, it is necessary to include instances of each coding in the training set , And here it is q Is a text representation based on encoding , therefore , What we learn is The relationship between texts , It has nothing to do with the specific code .
Training
Cross entropy is used to calculate the difference between the prediction probability and the actual label :
边栏推荐
- FISCO bcos zero knowledge proof Fiat Shamir instance source code
- 2022 P cylinder filling test content and P cylinder filling simulation test questions
- 《牛客刷verilog》Part II Verilog进阶挑战
- 论文阅读_中文NLP_ELECTRA
- Hj35 serpentine matrix
- UiPath实战(08) - 选取器(Selector)
- Golang -- realize file transfer
- Dive Into Deep Learning——2.1数据操作&&练习
- [set theory] binary relationship (binary relationship notation | binary relationship from a to B | number of binary relationships | example of binary relationship)
- [BMZCTF-pwn] 20-secret_ file
猜你喜欢
Why should programmers learn microservice architecture if they want to enter a large factory?
"Niuke brush Verilog" part II Verilog advanced challenge
Know that Chuangyu cloud monitoring - scanv Max update: Ecology OA unauthorized server request forgery and other two vulnerabilities can be detected
When using the benchmarksql tool to preheat data for kingbasees, execute: select sys_ Prewarm ('ndx_oorder_2 ') error
Jincang KFS data bidirectional synchronization scenario deployment
2022 t elevator repair simulation examination question bank and t elevator repair simulation examination question bank
Php+mysql registration landing page development complete code
FFMpeg filter
When using the benchmarksql tool to test the concurrency of kingbasees, there are sub threads that are not closed in time after the main process is killed successfully
[set theory] relational representation (relational matrix | examples of relational matrix | properties of relational matrix | operations of relational matrix | relational graph | examples of relationa
随机推荐
Dive Into Deep Learning——2.1数据操作&&练习
Market status and development prospect prediction of the global forward fluorescent microscope industry in 2022
《牛客刷verilog》Part II Verilog进阶挑战
逆袭大学生的职业规划
2022 tea master (intermediate) examination questions and tea master (intermediate) examination skills
Valentine's day limited withdrawal guide: for one in 200 million of you
[set theory] relational representation (relational matrix | examples of relational matrix | properties of relational matrix | operations of relational matrix | relational graph | examples of relationa
Why should programmers learn microservice architecture if they want to enter a large factory?
Jincang KFS data bidirectional synchronization scenario deployment
The programmer went to bed at 12 o'clock in the middle of the night, and the leader angrily scolded: go to bed so early, you are very good at keeping fit
SSM based campus part-time platform for College Students
Introduction to JVM principle
有道云笔记
Library management system based on SSM
Small program animation realizes the running lantern and animation object
I stepped on a foundation pit today
When using the benchmarksql tool to preheat data for kingbasees, execute: select sys_ Prewarm ('ndx_oorder_2 ') error
Market status and development prospect prediction of the global fire extinguisher industry in 2022
Day 51 - tree problem
AWS VPC