Archives par mot-clé : LS2N
Project AILE – AI for Learning Environments
Le LS2N a obtenu un soutien financé des Actions Exploratoires du CominLab pour un projet structurant d’un an qui vise à rapprocher des chercheurs de plusieurs équipes au LS2N et à l’IMT Atlantique impliqués dans des projets en lien avec l’enseignement, l’apprentissage et la formation “en ligne”. L’objectif est de préparer l’augmentation de leurs activités dans le thème pour les cinq prochaines années.
Parmi les actions pour construire cet éco-système, différentes activités scientifiques régulières seront mises en place (tenue de séminaires transversaux, organisation d’événements, recrutement de stagiaires, participation à colloques…).
[En savoir plus]MappSent, measuring Text-to-Text Similarity
MappSent, Python system implementing a Mapping Approach for measuring Text-to-Text Similarity
- Based on a linear text segment (e.g. sentence) embedding representation, its principle is to build a matrix that maps text segments in a joint-subspace where similar sets of segments are pushed closer.
- We evaluate our approach on the SemEval 2016 and 2017 question-to-question similarity task and show that overall MappSent achieves competitive results and outperforms in most cases state-of-art methods.
Download the sources (under Apache v2 license)
EXIDE, Extracting information from presentation
EXIDE, Python module for information extraction (logical structure…) from presentation documents
- Supported file types: Office Open XML (PPTX), OpenDocument (ODP), LaTeX beamer
- Among the extracted information: general presentation structure and outline, slide titles, body text, emphasized text, …
Download the sources (under a GNU GPL v3 license)
PyRATA, Python Rule-based feAture sTructure Analysis
- provides regular expression (re) matching methods on a more complex structure than a list of characters (string), namely a sequence of features set (i.e.
listofdictin python jargon); - is free from the information encapsulated in the features and consequently can work with word features, sentences features, calendar event features… Indeed, PyRATA is not only dedicated to process textual data.
- is fun and easy to use to explore data for research study, solve deterministic problems, formulate expert knowledge in a declarative way, prototype quickly models and generate training data for Machine Learning (ML) systems, extract ML features, augment ML models…
Download the sources (under Apache v2 license)