Skip to content
This repository has been archived by the owner on Nov 22, 2022. It is now read-only.

Vocab Limited Pretrained Embedding [2/5] #1248

Closed
wants to merge 1 commit into from

Commits on Feb 13, 2020

  1. Vocab Limited Pretrained Embedding [2/5]

    Summary: In local bento experiments, often nearest neighbors / items nearby in the embedding space tended to be misspellings of the original word. This isn't really useful for spoken language since there won't be many misspellings, so instead this diff adds a subclass of `PretrainedEmbeddings` that restricts the embedding space to only contain known vocab words. From local experiments, the results here seem much more consistent with what is expected from kNN in the embedding space.
    
    Reviewed By: geof90
    
    Differential Revision: D19818803
    
    fbshipit-source-id: bfac18887990f7a816e30000f8fbbfad37788fd3
    Akshat Shrivastava authored and facebook-github-bot committed Feb 13, 2020
    Configuration menu
    Copy the full SHA
    3418a08 View commit details
    Browse the repository at this point in the history