Text and Data miners

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 techn...

The objective of this tutorial is to showcase how the Neuroscience use case available at the OpenMinTeD platform can facilitate the curation of neuroscience entities from the literature with the aim of supporting ongoing curation efforts in the Blue Brain Project (BBP), at the École Polytechnique Fédérale de Lausanne (EPFL).
 

The objective of this tutorial is to showcase the use case of “Extract Metabolites and their Properties and Modes of Actions”. The tutorial describes step-by-step how to create a workflow in the OpenMinTeD platform that can read input from a source and annotate entities useful for the curation of the ChEBI database.
 

This tutorial explains how to use the “Arabidopsis Gene Regulation Extractor” application available from the OpenMinTeD platform. It also explains the scientific issues it addresses, and how results of the TDM process can be exploited by researchers through the FlagDB++ application. It is related to the AS-D “Information Extraction of Mechani...

This tutorial explains how to use the “Habitat-Phenotype Relation Extractor for Microbes” application available from the OpenMinTeD platform. It also explains the scientific issues it addresses, and how the results of the TDM process can be queried and exploited by researchers through the Florilège application. It is related to the AS-C “Micr...

The Unstructured Information Management Architecture (UIMA) is a widely used software framework and specification to create multi modal analysis systems, in particular for Natural Language Processing (NLP) purposes. Especially, the OpenMinted platform builds upon this architecture enhancing the need for NLP tools that comply to UIMA.In this t...

The purpose of this tutorial is to explain how to add annotation resources to the OMTD platform. In this context, annotation resources mean ontologies or vocabularies selected in different ontology repositories like AgroPortal.
 

BO-LSTM is a model based on biomedical ontologies and Long short-term memory networks. The model was developed in python, using keras. To demonstrate its utility, we trained a classification model on the DDI corpus, using the ChEBI ontolo...

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, disambigua...

Abbreviations and basic subject-object relations can be valuable data to understand the context and meaning of text passages. This tutorial explains how to use the two tools Ab3P and OpenSesamIE to extract this data in aggregate. Both tools are integrated into OpenMinTeD using the PubRunner framework which manages format conversion and many o...