claws-lab / misinfocorrect Goto Github PK
View Code? Open in Web Editor NEWCode and Data for WWW'23 paper Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation
Code and Data for WWW'23 paper Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation
Hi.
I have just a question about the loss function: in the paper, the loss is defined as L = -r * log(p(\hat(c)|m)), where r is the reward and p is the probability to generate \hat(c) given the message m.
Now, to the best of my comprehension, the second term should be negative (since p is a probability) and r should be positive (or zero). Hence, the final loss should be positive as well.
In the code, instead, another "-" is added to the second term, resulting in a final negative loss.
Is it correct? If yes, what is the rationale?
Thank you in advance for your kind response.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.