joaoDossena/BERTopic-Tatoeba-PT

Introduction

BERTopic-Tatoeba-PT is a topic model based on BERTopic (Grootendorst [2022]) with default parameters, using Tatoeba sentences in Portuguese with English translations as documents. BERTopic-Tatoeba-PT was developed in the context of the Master's thesis "Learning What to Learn: Generating Language Lessons using BERT", whose repository with code and text is available on Github.

Usage

!pip install bertopic
from bertopic import BERTopic

# Load model
topic_model = BERTopic.load("bertopic_portuguese_tatoeba_5k")