Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add L2p/Lkp to the feature set #28

Open
lgrz opened this issue Apr 16, 2020 · 0 comments
Open

Add L2p/Lkp to the feature set #28

lgrz opened this issue Apr 16, 2020 · 0 comments

Comments

@lgrz
Copy link
Contributor

lgrz commented Apr 16, 2020

From Efficient and Effective Higher Order Proximity Modeling. The intervals for L2p, Lkp and Lkfp methods are computed using lazy/eager plane sweep Lu et al, (CIKM 15).

Computing intervals. There are a number of options for computing intervals which can impact efficiency, details are in the CIKM paper. The options are:

  • Eager plane sweep
  • Lazy plane sweep
  • Traversal of inverted file (with positional information)
  • Traversal of direct file

Reported in the CIKM paper is that traversal over the inverted file works best for shorter documents, while using the direct file serves better with longer documents.

An ideal solution would be to support all combinations of methods. However currently there is no support for positional inverted index files, so that would need to be added for inverted file traversal.

With this in mind a first pass on implementing this will use the direct file approach and consider the inverted file approach afterwards.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

1 participant