songjiang0909 / boxtaxo Goto Github PK
View Code? Open in Web Editor NEWCode for paper "A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings"
Code for paper "A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings"
According to the code given, after I ran through it, I found that the results of both the environmental data set and the scientific data set were quite different from those given in the paper.Aside from creating the file, importing the package, and changing the beta value to 0.1(which corresponds to the value given at the end of the paper), I only did two things when debugging the code.
First thing: Added a command to the main.py:parser.add_argument('--model', type=str, default='vec', help='model type'),Used to solve the vec parameter problem in data.py.
The second thing is:When running the main.py, there was an error importing"../data/"+str(dataset)+"/raw/"+str(dataset)+"_raw_en.taxo".In the file downloaded by the platform, the dataset does not have this file. I had to change this to"../data/"+str(dataset)+"/"+str(dataset)+"_all.taxo".I can't get the desired result after only making these changes. Could you please give me some guidance on how to change to get the desired effect?
Science:
Environment:
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.