This project, currently in its early stages, aims to implement N-gram counting, smoothing, and interpolation. The project may eventually incorporate a number of smoothing methods, but initially it will incorporate just one, which is not a standard method. It's similar in spirit but modified, interpolated Kneser-Ney, but uses the principle that the amount you discount should always be the amount that gets given to the backoff state (which makes the traditional count-of-counts stuff and the associated formulas for obtaining smoothing constants unusuable).
This gives slightly better results than KN for standard LM building, but has larger advantages for interpolation and pruning. See <a href=freelm.sf.net> here </a> for documentation.

Project Activity

See All Activity >

Categories

Linguistics

License

Apache License V2.0

Follow FreeLM

FreeLM Web Site

nel_h2
Simply solve complex auth. Easy for devs to set up. Easy for non-devs to use. Icon
Simply solve complex auth. Easy for devs to set up. Easy for non-devs to use.

Transform user access with Frontegg CIAM: login box, SSO, MFA, multi-tenancy, and 99.99% uptime.

Custom auth drains 25% of dev time and risks 62% more breaches, stalling enterprise deals. Frontegg platform delivers a simple login box, seamless authentication (SSO, MFA, passwordless), robust multi-tenancy, and a customizable Admin Portal. Integrate fast with the React SDK, meet compliance needs, and focus on innovation.
Start for Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of FreeLM!

Additional Project Details

Operating Systems

Linux

Intended Audience

Science/Research

User Interface

Command-line

Programming Language

C++

Related Categories

C++ Linguistics Software

Registered

2012-02-25