Jan. 24, 2022, 1:36 p.m. | Thomas Wong

Towards Data Science - Medium towardsdatascience.com

Introduction to the idea of vector representations and compare TF-IDF vectors with SentenceTransformers vectors!

Image by Author.

Background

Before I joined HK01, its data team has already been leveraging the enormous amount of text data to build several data projects. While it is good to be able to apply NLP (Natural Language Processing) techniques to real-world data to make an impact on the business, I noticed that these data projects are all using TF-IDF to learn the embeddings (vector …

nlp sentence-embedding transformers word embeddings

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Intern Large Language Models Planning (f/m/x)

@ BMW Group | Munich, DE

Data Engineer Analytics

@ Meta | Menlo Park, CA | Remote, US