Hub
  • Software
  • Blog
  • Forum
  • Events
  • Documentation
  • About KNIME
Sign in
  • KNIME Hub
  • knime
  • Spaces
  • Examples
  • 08_Other_Analytics_Types
  • 01_Text_Processing
  • 27_Semantic_Search_with_BERT
WorkflowWorkflow

Semantic Search with BERT

tensorflow tensorflow2 BERT semanticsearch

Last update: 

Drag Workflow
Workflow preview
In this workflow, abstracts from the COVID-19 Open Research Dataset (https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge) are read in to perform semantic search using a TensorFlow 2 BERT model. For this purpose, a BERT model that has already been trained on the CORD-19 dataset is loaded from TensorFlow Hub (https://tfhub.dev/tensorflow/cord-19/swivel-128d/3). The BERT embeddings created from the abstracts are used to find semantically similar abstracts for the question asked; they are used to calculate the cosine similarity to the query embeddings and the semantically most relevant papers are displayed in a view afterwards. The data can be downloaded from https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge

Used extensions & nodes

Created with KNIME Analytics Platform version 4.2.2
  • KNIME Base nodes Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.2

  • KNIME Deep Learning - Keras Integration Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.1

  • KNIME Deep Learning - TensorFlow 2 Integration Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

  • KNIME Excel Support Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.1

  • KNIME JavaScript Views Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.2

  • KNIME Javasnippet Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.0

  • KNIME Python Integration Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.2

  • KNIME Quick Forms Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.2

  • KNIME Textprocessing Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.2.1

Legal

By downloading the workflow, you agree to our terms and conditions.

License (CC-BY-4.0)
Short link
Discussion
Discussions are currently not available, please try again later.

KNIME
Open for Innovation

KNIME AG
Hardturmstrasse 66
8005 Zurich, Switzerland
  • Software
  • Getting started
  • Documentation
  • E-Learning course
  • Solutions
  • KNIME Hub
  • KNIME Forum
  • Blog
  • Events
  • Partner
  • Developers
  • KNIME Home
  • KNIME Open Source Story
  • Careers
  • Contact us
Download KNIME Analytics Platform Read more on KNIME Server
© 2021 KNIME AG. All rights reserved.
  • Trademarks
  • Imprint
  • Privacy
  • Terms & Conditions
  • Credits