Comments (2)
I get the answer from the paper ...
from sequicity.
Hi,
Thanks for your question. According to our paper, the input of the model is the concatenation of the response of the previous turn and the user input of current turn. We have followed our baseline https://github.com/shawnwun/NNDIAL, and we believe it is a standard practice.
from sequicity.
Related Issues (19)
- config error when fine-tuning with rl
- KeyError when using pytorch 0.4.0 HOT 1
- Data Processing Is Wrong HOT 6
- A Serious Problem In Your Model HOT 1
- During the decoding time,where do you use information of response HOT 1
- Why does function _extract_request() in metric.py use EOS_Z1 as end mark instead of EOS_Z2? HOT 2
- decoder result is strange HOT 4
- Poor performance of the trained model HOT 1
- Is it possible for decoding the real slot-value? HOT 2
- KeyError: 'generated_latent'
- About CopyNet HOT 1
- About Reinforcement Learning
- 正则表达式
- Unlexicalized results HOT 1
- Typo in metric.py
- two questions about reader.py HOT 2
- The content in the tokenized kvret files seems to be wrong HOT 3
- something wrong while testing kvret ,how to solve it HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sequicity.