Comments (6)
Thank you for your interest in our study.
What is dataset you used?
I think your dictionary (vocabulary) size is too large and thus, out of memory error is happened.
from control-length.
Thank you for your answer, I used WrittingPrompts from here https://dl.fbaipublicfiles.com/fairseq/data/writingPrompts.tar.gz.
from control-length.
I'm not familiar with the dataset. So, if you want to apply a neural encoder-decoder to the dataset, I recommend asking the publisher of the dataset.
As described, I think your vocabulary size is too large, thus, recommend using subword such as BPE or sentencepiece to construct vocabulary.
from control-length.
Ok thanks. What dataset did you use? Is it available for public use?
from control-length.
We conducted experiments on summarization as described in our paper: https://www.aclweb.org/anthology/N19-1401.pdf
We used Annotated English Gigaword which is not publicly available officially but distributed in https://github.com/harvardnlp/sent-summary
The above distributed dataset might be pre-processed but we need to construct subword vocabulary for encoder-decoders.
from control-length.
Thank you, reducing the dataset size did it.
from control-length.
Related Issues (7)
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 control-length.