yinghy18 / credel Goto Github PK
View Code? Open in Web Editor NEWThe code repository of the paper "Label Refinement via Contrastive Learning for Distantly-Supervised Named Entity Recognition"
The code repository of the paper "Label Refinement via Contrastive Learning for Distantly-Supervised Named Entity Recognition"
First we should train the CReDEL main part ---- the contrastive model. simply run: cd ./contrastive_model_training python main.py Then we need to train a entity typing module. Take the training data is consist of raw_train.txt and tagged_train.txt in ./data/; the UMLS is in ./dict/ The format of tagged file is [{"begin":i, "end":j, "pharse":"the pharse"},...]. The training command is: python main.py --train_batch_size 256 --save_step 1000 --gradient_accumulation_steps 16 --learning_rate 0.00005 --train_epoch 3 Finally we need to refine the DSNER dataset for DSNER methods. Take the BC5CDR dataset annotated by UMLS subset. Simply: run refine_label.sh #pretrained models and data not provided in this source code due to copyright issues, #but we provide the data generation method in the paper.
tx = sample['tokens']
tg2 = sample['y2']
tg1 = sample['y1']
tg = sample['y']
想请教下作者,tg、tg1和tg2是什么样的一个序列,可否给出例子
hi, I am reading your paper ,and want to test the effect. Would you mind publishing your dataset? including the BC5CDR and NCBI-Disease distant label data. thanks!!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.