Text Analytics Toolbox Model for UDify Data

Pretrained Deep Learning Model for Universal Dependency Annotation using Text Analytics Toolbox

This add-on provides a pre-trained deep learning model for dependency parsing using Universal Dependency Annotation with Text Analytics Toolbox. Dependency parsing is used to extract relationship between words in a sentence in Natural Language Processing (NLP). The pretrained model builds on BERT (deep learning transformer model) to extract dependency tree information for multiple languages, as defined by Universal Dependencies. For more information on the data, see: https://github.com/Hyperparticle/udify.

Opening udifymodel.mlpkginstall file from your operating system or from within MATLAB will initiate the installation process for the release you have. This mlpkginstall file is functional for R2022b and beyond.

Usage Example:

% See the last two columns for dependency details, after running the following code:

>> document = tokenizedDocument("Wherever you go, there you are.");

>> document = addDependencyDetails(document);

>> tokenDetails(document)

% Visualize dependency tree

>> sentenceChart(document)