recommenders-team/recommenders

Implementing BERT embeddings into NPA model

Open

#1,604 opened on Jan 6, 2022

View on GitHubContributor guide
 (2 comments) (1 reaction) (0 assignees)Python (3,319 forks)batch import
help wanted

Repository metrics

Stars
 (21,861 stars)
PR merge metrics
 (Avg merge 6d 16h) (10 merged PRs in 30d)

Description

Description

Hello Evryone,

I tried to use BERT embeddings with the NPA model, I generated the embeddings for the news titles, but I didn't understand what changes should I make in my code to get the real results of the BERT embeddings with NPA.

Other Comments

Contributor guide

Research direction
Investigate how to integrate BERT embeddings into the NPA model by examining the NPA model's input format and modifying the data preprocessing pipeline to use BERT embeddings instead of word embeddings. Look at existing implementations of BERT in recommendation models for guidance.
Tech stack
python
Domain
backendmachine learning
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
PythonNLP
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60