Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia

TL;DR

Wikipedia2Vec is an open-source toolkit that efficiently learns and visualizes word and entity embeddings from Wikipedia, achieving state-of-the-art results and supporting multiple languages.

Contribution

It introduces a user-friendly, efficient tool for learning and visualizing Wikipedia-based embeddings, with pretrained models and a web demo for exploration.

Findings

Achieved state-of-the-art results on KORE dataset

Demonstrated competitive performance on standard benchmarks

Supported multiple languages with pretrained embeddings

Abstract

The embeddings of entities in a large knowledge base (e.g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge. In this paper, we present Wikipedia2Vec, a Python-based open-source tool for learning the embeddings of words and entities from Wikipedia. The proposed tool enables users to learn the embeddings efficiently by issuing a single command with a Wikipedia dump file as an argument. We also introduce a web-based demonstration of our tool that allows users to visualize and explore the learned embeddings. In our experiments, our tool achieved a state-of-the-art result on the KORE entity relatedness dataset, and competitive results on various standard benchmark datasets. Furthermore, our tool has been used as a key component in various recent studies. We publicize the source code, demonstration, and the pretrained embeddings for 12 languages at https://wikipedia2vec.github.io.