• 2017-2021close
• Software close
• European Commission close
• EU close
• Digital Humanities and Cultural Heritage close

A Jupyter Notebook implementing a simple parser used to transform the Multilingual Data Stewardship terminology and Metadata, created in the Task 3.1 of the SSHOC project, into SKOS resources. The parser transforms the content in SKOS data following a set of mapping rules, the result is stored in two Turtle files.

This code demonstrates generic public examples of a Simple IIIF Discovery system, based on tools used within the National Gallery to provide access to images from multiple institutions and present them together in IIIF compatible viewers. The system is based on a website requesting the details of IIIF images from a Simple IIIF Discovery end-point, based on a simple keyword search. The website does not need to understand the complexities of any underlying APIs, just the simple structure of the results returned by the end-point. The website then just needs to be able to reformat the IIIF results and feed them into a IIIF based viewer of choice. This version includes a number of updates to the original demonstrator related to improving the user interface, including adding a toggle option to jump between IIIF viewers, and updating the administration process of creating new end-points and related web-pages, this is all achieved via a simple JSON config files now. A working demo of this system can be seen at: https://research.ng-london.org.uk/ss-iiif

Marian NMT model for Catalan to Occitan translation. It is a multi-task model, producing also a phonemic transcription of the Catalan source. The model was submitted to WMT'21 Shared Task on Multilingual Low-Resource Translation for Indo-European Languages as a CUNI-Contrastive system for Catalan to Occitan.

Marian multilingual translation model from Catalan into Romanian, Italian and Occitan. Primary CUNI submission for WMT21 Multilingual Low-Resource Translation for Indo-European Languages Shared Task.

Marian NMT model for Catalan to Occitan translation. Primary CUNI submission for WMT21 Multilingual Low-Resource Translation for Indo-European Languages Shared Task.

This submission contains Dockerfile for creating a Docker image with compiled Tensor2tensor backend with compatible (TensorFlow Serving) models available in the Lindat Translation service (https://lindat.mff.cuni.cz/services/transformer/). Additionally, the submission contains a web frontend for simple in-browser access to the dockerized backend service. Tensor2Tensor (https://github.com/tensorflow/tensor2tensor) is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

This is a simple set of processes for creating a standard set of webpages based on a simple set of json files. This project is intended to work along side other projects to provide a simple way of creating a set of consistent webpages, which can be delivered as part of your own GitHub project using GitHub pages. It has been extended to allow more complex features such as presenting IIIIF (https://iiif.io) viewers, Timelines, and ordered Lists & Galleries. Various updates to the related JavaScript libraries have been added along with an option to use the whole system to create dynamic as well as static websites. For more detail and the most current version of the code see: https://github.com/jpadfield/simple-site

This is an interactive live modelling system which can automatically convert simple tab separated triples or JSON-LD into graphical models using the mermaid library. General updates and improvements have been carried out, with the addition of the Mermaid SubGraph functionality to aid the organisation of more complex models. Instructions: Full details and instructions relating to how this system works is still being developed, however several examples are included in the interactive web site: dynamic modelling, with all of the related code presented in GitHub.

En-De translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). Models are compatible with Tensor2tensor version 1.6.6. For details about the model training (data, model hyper-parameters), please contact the archive maintainer. Evaluation on newstest2020 (BLEU): en->de: 25.9 de->en: 33.4 (Evaluated using multeval: https://github.com/jhclark/multeval)

CUBBITT En-Fr translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). Models are compatible with Tensor2tensor version 1.6.6. For details about the model training (data, model hyper-parameters), please contact the archive maintainer. Evaluation on newstest2014 (BLEU): en->fr: 38.2 fr->en: 36.7 (Evaluated using multeval: https://github.com/jhclark/multeval)