Skip to content
Phuc Tran Truong edited this page Jun 6, 2020 · 1 revision

Welcome to the FBMTC wiki!

This project is part of the Seminar "Klassifikation Biomedizinischer Texte" at the Humboldt-University of Berlin. We will use the NLP Framework Flair (Flair Embeddings in particular) to do biomedical text classification. For a quick overview on Flair take a look at: https://research.zalando.com/welcome/mission/research-projects/flair-nlp/

We are given a data set of 15301 abstracts of biomedical articles.

Goal: Implement a classification pipeline to perform the following tasks

  1. Is the article concerned with cancer? (yes / no)
  2. About which specific type of cancer is the article about? (multi-class)
Clone this wiki locally