Programmers

Navigation

Resources

Universidade do Minho, Secretaria de Estado da Ciência, Tecnologia e Ensino Superior, FCT-FCCN – Fundação para a Ciência e Tecnologia
Instituto Politécnico de Castelo Branco, portugal
16.11.2018
Intended audience Programmers, Researchers and Students, Text and Data miners
Level: Advanced: apply

The Freeling component provides basic language analysis functionalities (tokenization, lemmatization, Pos Tagging and dependency parsers.) for the variety of languages that Freeling includes (English, Spanish, Portuguese, Italian, French, German, Russian, Catalan, Galician, Croatian, Slovene). The specific usage scenario for this component concerns scientific publications in non-English languages. The component has been shared as a Docker a...

Intended audience Programmers, Researchers and Students, Text and Data miners
Level: Advanced: apply

The objective of this component is to scan a tokenized text to detect entries in BabelNet in the input document. This component is the base of entity linking and word sense disambiguation as it detects the candidates to be disambiguated. The component produces WSD item annotations as defined in the DKPro WSD typesystem. Afterwards, disambiguation can be performed by other components (like DKPro WSD). The component has been shared as a Docke...

Intended audience Industry and Business, Programmers, Project Managers, Publishers, Researchers and Students, Text and Data miners
Level: Introductory: no previous knowledge is required

This tutorial includes three parts that describe how to use the Wheat Phenotypic Information Extractor and the two end-user applications, WheatIS and AlvisIR, that integrates its results for the use case developed by Inra during the OpenMinTeD project.The application extracts information related to wheat on phenotypes, genes, markers, species, and varieties.

EOSC-hub, GÉANT, OpenAIRE and PRACE
ISCTE, Lisbon
09.10.2018 - 11.10.2018
Intended audience Policy makers and Funders, Programmers, Researchers and Students, Text and Data miners
Level: Introductory: aware of

This tutorial describes how to use TDM to build a Recommender system for scholarly resources and utilise OpenMinTed platform to build and annotate corpuses for this purpose.

Intended audience Industry and Business, Programmers, Researchers and Students, Text and Data miners
Level: Introductory: no previous knowledge is required

In this course we will explain how IXA pipes have been integrated as Docker images in the OpenMinTeD (OMTD) platform and how can they be used (http://ixa2.si.ehu.es/ixa-pipes/).

The aim of IXA pipes is to provide a modular set of ready to use Natural Language Processing (NLP) tools. IXA pipes uses the same approach across NLP tasks in order to create robust processors both across domains and languages.
 

&nbs...

Intended audience Text and Data miners, Industry and Business, Programmers, Researchers and Students
Level: Introductory: no previous knowledge is required

This tutorial focuses on using the Docker image to annotate raw text files. It shows how to install the docker system on a machine, how to pull the UPFMT image and how to pass the input/output parameters and instantiate the container. The user simply has to provide an input folder containing any number of files to be annotated (.txt or .xmi) and an output folder where the annotated files (.conllu and .xmi) will be generated. No programming ...

Intended audience Text and Data miners, Industry and Business, Programmers, Researchers and Students, Text and Data miners
Level: Introductory: aware of

This tutorial focuses on using the code directly on a host machine. It gives access to the code (Python) + models and shows the user how to run the code from the console. Also, all the steps needed on how to train new models are given, as well as other pointers. The user will be able to download the code, run a tokenizer/tagger/parser on a set of files (either .xmi or .txt) and obtain as output the annotated files (conllu format).
&n...

Intended audience Programmers, Researchers and Students, Text and Data miners
Level: Intermediate: able to

In the current context of scientific information overload in which new knowledge is created at a rapid pace, we propose to develop text summarization services for automatically identifying the most important information of a research article. The work will be based on an adaptation of our current scientific text mining and summarization technology at our  LaSTUS/TALN lab. The summarization system will apply a natural language processin...