论文标题
超越t-sne：在文本嵌入中展示\ texttt {WhatLies}
Going Beyond T-SNE: Exposing \texttt{whatlies} in Text Embeddings
论文作者
论文摘要
我们介绍Whatlies，这是一种用于视觉检查单词和句子嵌入的开源工具包。该项目提供了一个统一且可扩展的API，目前支持一系列流行的嵌入后端，包括Spacy，TFHUB，HuggingFace Transfceers，Gensim，Gensim，FastText和Bytepair Embeddings。该软件包将矢量算术的特定域语言与可视化工具相结合，使探索单词嵌入更加直观和简洁。它为许多流行的维度降低技术以及许多可以通过jupyter笔记本电脑静态导出或共享的交互式可视化提供了支持。该项目文档可从https://rasahq.github.io/whatlies/获得。
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/.
