Year: 2019
Type: article
Abstract: Embeddings.jl is a tool to help users of the Julia programming language (Bezanson, Edelman, Karpinski, & Shah, 2017) make use of pretrained word embeddings for natural language processing.Word embeddings are a very important feature representation in natural language processing.The use of embeddings pretrained on very large corpora can be seen as a form of transfer learning.It allows knowledge of lexical semantics derived from the distributional hypothesis-that words occurring in similar contexts have similar meaning-to be injected into models which may have only limited amounts of supervised, task oriented training data.
DOI: 10.21105/joss.01013
Authors: Lyndon White, David Ellison
Institution: The University of Western Australia
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2936618633