Deep Learning

An Adaptive Layer to Leverage Both Domain and Task Specific Information from Scarce Data

In this paper, we present our method, TAFT, to enhance model adaptation both on domain and task especially for small datasets. To demonstrate it we consider the use-case of customer service chats.

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

In this work we present ProtoSeq, an adaptation of the Prototypical Networks to enable dealing with sequences in a few-shot learning way, reducing the need for labeling confidential data. [...]

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

In this work, we place ourselves in the scope of a live chat customer service in which we want to detect emotions and their evolution in the conversation flow. This context leads to multiple challenges [...]

Meta-learning for Classifying Previously Unseen Data Source into Previously Unseen Emotional Categories

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 [...]

Méta-apprentissage : classification de messages en catégories émotionnelles inconnues en entraînement

Dans cet article nous reproduisons un scénario d'apprentissage selon lequel les données cibles ne sont pas accessibles et seules des données connexes le sont. [...]

Multilingual Fake News Detection with Satire

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

On the Use of Dependencies in Relation Classification of Text with Deep Learning

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

EmoReco

EMOtional EMOji RECOmmendation system. Web interface to use and evaluate the recommendation system in a textual chat.

FaceEmojis

Emoji Embeddings and Clusters of Face Emojis. This is the source code from a paper we presented to CICLing 2018, please cite this paper if you find this work useful.

LIS at SemEval-2018 Task 2: Mixing Word Embeddings and Bag of Features for Multilingual Emoji Prediction

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.