travel-go / abstractive-text-summarization Goto Github PK
View Code? Open in Web Editor NEWContrastive Attention Mechanism for Abstractive Text Summarization
License: Other
Contrastive Attention Mechanism for Abstractive Text Summarization
License: Other
你好,可以分享一下LCSTS2.0原始数据集吗?我按官方的填写了申请,一直没有收到他们的回信,CSDN的链接也失效的,多谢。[email protected]
Hi,
Thanks for open-sourcing your code !
How can we reproduce your paper's results ?
As I understood your paper, opponent attention is trained through softmin
.
softmin
is actually the reason why conventional attention and opponent attention are trained in an opposite fashion.
However, what's the point of the opponent function ?
If the opponent function was removed, it would be the equivalent of another attention head, trained negatively
(because of softmin
).
So why adding such an function, which as I understand it simply mask existing conventional attention scores (therefore loosing information ?) ?
I'm confused about one detail in your paper.
From Figure 1, it seems the contrastive attention mecanism is applied to each decoder layer :
But from the text, it is mentioned that each attention head have different responsability and you hand-picked the best one :
So I'm not sure if the contrastive mecanism is applied to every head of the model or only the one you chose.
when I run train.py
, an error occured and said 'no module named data', then I copied the data
module from pytorch's fairseq(version 0.8), more errors come out, which fairseq`s version in your code?
Can you give me a command for running or necessary args for training the model for summarization? The code is prepared for machine translation instead of summarization, so we are hard to infer the specific arguements.
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.