constantinelignos / morsel Goto Github PK
View Code? Open in Web Editor NEWMORphological Sparsity Embiggens Learning: A simple unsupervised morphological learning model.
License: GNU General Public License v3.0
MORphological Sparsity Embiggens Learning: A simple unsupervised morphological learning model.
License: GNU General Public License v3.0
Hi Constantine,
Thanks for your work on MORSEL. I am testing it out for a research project at my lab, and I noticed that there seems to be an overflow error in the code.
Here is what I see when I start it up with my lexicon:
Loading words...
2583018 types loaded...
-1910967574 tokens loaded.
Init time: 45.85s
Lexicon stats:
Types: 2583018 Tokens: -1910967574
Handling hyphenation...
Lexicon stats:
Types: 2583018 Tokens: -1910967574
Memory status: 3657MB Used, 23501MB Remaining
Starting learning...
Iteration 1
Lexicon stats:
Types: 2583018 Tokens: -1910967574
Base size: 0
Derived size: 0
Unmodeled size: 2583018
Hypothesizing and scoring transforms...
Selecting a transform...
I am not sure if this overflow is going to mess up anything else, but I thought you might want to know. I think if you used a 64 bit integer instead of a 32 bit integer, it might avoid this problem.
Thanks,
Cyrus Shaoul
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.