Skip to content
This repository has been archived by the owner on Dec 14, 2020. It is now read-only.

Apply BERT sentence embeddings to find similar sentences in a context-aware approach.

License

Notifications You must be signed in to change notification settings

YevheniiSemendiak/text_matcher

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Text Matcher 🔍

Utility for storing texts in sentence-wise approach and searching for similar sentences in a context-aware approach.
Based on BERT NLP model (bert-base-nli-mean-tokens).

Deployment

  1. Clone repository with git clone git@github.com:YevheniiSemendiak/text_matcher.git;
  2. Deploy TextMatcher with docker-compose up --build;

Usage

  1. Simple CLI tool.

    • Being in text_matcher/back folder hit python3 simple_cli.py.
    • Requires pika and pymongo Python3 modules installed.
  2. Web GUI:

    • Build using Vue.js & Vuetify.js frameworks.
    • Add, read texts and compare sentences.

Questions or Suggestions?

Contact me at TG or 📧.