Going Beyond T-SNE: Exposing whatlies in Text Embeddings

09/04/2020
by   Vincent D. Warmerdam, et al.
0

We introduce whatlies, an open source toolkit for visually inspecting word and sentence embeddings. The project offers a unified and extensible API with current support for a range of popular embedding backends including spaCy, tfhub, huggingface transformers, gensim, fastText and BytePair embeddings. The package combines a domain specific language for vector arithmetic with visualisation tools that make exploring word embeddings more intuitive and concise. It offers support for many popular dimensionality reduction techniques as well as many interactive visualisations that can either be statically exported or shared via Jupyter notebooks. The project documentation is available from https://rasahq.github.io/whatlies/.

READ FULL TEXT

page 4

page 5

page 6

page 7

research
09/05/2019

Fusing Vector Space Models for Domain-Specific Applications

We address the problem of tuning word embeddings for specific use cases ...
research
08/11/2017

Simple and Effective Dimensionality Reduction for Word Embeddings

Word embeddings have become the basic building blocks for several natura...
research
06/05/2021

Denoising Word Embeddings by Averaging in a Shared Space

We introduce a new approach for smoothing and improving the quality of w...
research
12/02/2021

Interactive Visualization of Spatial Omics Neighborhoods

Dimensionality reduction of spatial omic data can reveal shared, spatial...
research
04/06/2021

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Word vector embeddings have been shown to contain and amplify biases in ...
research
06/22/2023

Vec2Vec: A Compact Neural Network Approach for Transforming Text Embeddings with High Fidelity

Vector embeddings have become ubiquitous tools for many language-related...
research
04/27/2019

Enabling Open-World Specification Mining via Unsupervised Learning

Many programming tasks require using both domain-specific code and well-...

Please sign up or login with your details

Forgot password? Click here to reset