Gaël Guibon (gguibon)

gguibon

Geek Repo

Company:University of Lorraine

Location:Nancy

Home Page:gguibon.github.io/

Twitter:@gguibon

Github PK Tool:Github PK Tool


Organizations
Arborator

Gaël Guibon's repositories

acl-2024

Repository for the ACL 2024 conference website

Language:JavaScriptLicense:NOASSERTIONStargazers:0Issues:0Issues:0

UL-webL2

Cours de Web Avancé - L2 - Université de Lorraine

Language:PHPLicense:AGPL-3.0Stargazers:0Issues:0Issues:0

M2-dm4nlp

Data Mining for NLP course - University of Lorraine

Language:Jupyter NotebookLicense:AGPL-3.0Stargazers:0Issues:0Issues:0
Language:HTMLStargazers:0Issues:0Issues:0

ezcat

EZCAT: an Easy Conversation Annotation Tool

Language:VueLicense:MITStargazers:5Issues:0Issues:0
Language:Jupyter NotebookLicense:AGPL-3.0Stargazers:0Issues:0Issues:0
License:NOASSERTIONStargazers:0Issues:0Issues:0

docs

Universal Dependencies online documentation

License:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonLicense:AGPL-3.0Stargazers:0Issues:0Issues:0
Language:JavaLicense:GPL-3.0Stargazers:3Issues:0Issues:0

ProtoSeq

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

Language:PythonLicense:AGPL-3.0Stargazers:12Issues:0Issues:0

metalearning-emotion-datasource

In this paper, we place ourselves in a classification scenario in which the target classes and data type are not accessible during training. We use a meta-learning approach to determine whether or not meta-trained information from common social network data with fine-grained emotion labels can achieve competitive performance on messages labeled with different emotion categories. We leverage few-shot learning to match with the classification scenario and consider metric learning based meta-learning by setting up Prototypical Networks with a Transformer encoder, trained in an episodic fashion. This approach proves to be effective for capturing meta-information from a source emotional tag set to predict previously unseen emotional tags. Even though shifting the data type triggers an expected performance drop, our meta-learning approach achieves decent results when compared to the fully supervised one.

Language:PythonLicense:AGPL-3.0Stargazers:3Issues:0Issues:0

LAKME-SRCMF-visu

GUI tool to gather different visualization of syntactic trees, their errors, and edit them in graphic mode.

Language:JavaScriptLicense:AGPL-3.0Stargazers:0Issues:0Issues:0

SRCMF-nlp-api

An API that regroups Natural Language Processing usages for the SRCMF.

Language:JavaLicense:AGPL-3.0Stargazers:0Issues:0Issues:0
Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0

essec-python-1

Introduction to programming (using python)

Language:HTMLLicense:AGPL-3.0Stargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

dev-meetup-inria

Presentation and example files for devmeetup

Language:Jupyter NotebookStargazers:0Issues:0Issues:0

quasar-awesome

🎉 A list of awesome things related to Quasar

License:MITStargazers:0Issues:0Issues:0

Telegram

Telegram for Android source

Language:JavaLicense:GPL-2.0Stargazers:0Issues:0Issues:0
Language:HTMLLicense:AGPL-3.0Stargazers:4Issues:0Issues:0

ginger

Format conversion and graphical representation of [Universal Dependencies](http://universaldependencies.org) trees.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

awesome-vue

🎉 A curated list of awesome things related to Vue.js

Stargazers:0Issues:0Issues:0

spring-boot-vuejs

Example project showing how to build a Spring Boot App providing a GUI with Vue.js

Language:VueLicense:MITStargazers:0Issues:0Issues:0

fcm

A Neural Network model for NLP (relation classification)

Language:C++License:MITStargazers:1Issues:0Issues:0

storyboarder

Storyboarder makes it easy to visualize a story as fast you can draw stick figures.

Language:JavaScriptStargazers:0Issues:0Issues:0
Language:PythonLicense:GPL-3.0Stargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

alchemancy

Alchemancy Mark III - Wonder Unit's drawing system

Language:TypeScriptStargazers:0Issues:0Issues:0

Sideshow

Sideshow is a powerful javascript library which aims to reduce your user's learning curve by providing a way to create step-by-step interactive tours. Explain the features of your application, control your end-user's interaction with your UI, emphasize what you're explaining in each step by masking it. Just think! The sky is the limit!

Language:JavaScriptLicense:Apache-2.0Stargazers:0Issues:0Issues:0