Search Results for author:
Found 16 papers, 3 papers with code
Adversarial Adaptation for French Named Entity Recognition
We propose a Transformer-based NER approach for French, using adversarial adaptation to similar domain or general corpora to improve feature extraction and enable better generalization.
Automatic Text Simplification of News Articles in the Context of Public Broadcasting
This report summarizes the work carried out by the authors during the Twelfth Montreal Industrial Problem Solving Workshop, held at Universit\'e de Montr\'eal in August 2022.
Personalized Student Attribute Inference
We compare a naive approach widely used in the literature, which uses attributes available in the data set (like the grades), with a personalized approach we called Personalized Student Attribute Inference (PSAI).
Transformer-Based Named Entity Recognition for French Using Adversarial Adaptation to Similar Domain Corpora
Named Entity Recognition (NER) involves the identification and classification of named entities in unstructured text into predefined classes.
Quick Starting Dialog Systems with Paraphrase Generation
Acquiring training data to improve the robustness of dialog systems can be a painstakingly long process.
An Iterative Contextualization Algorithm with Second-Order Attention
In order to achieve this, representations of words are built combining their symbolic embedding with a positional encoding into single vectors.
Du bon usage d'ingr\'edients linguistiques sp\'eciaux pour classer des recettes exceptionnelles (Using Special Linguistic Ingredients to Classify Exceptional Recipes )
Nous pr{\'e}sentons un mod{\`e}le d{'}apprentissage automatique qui combine mod{\`e}les neuronaux et linguistiques pour traiter les t{\^a}ches de classification dans lesquelles la distribution des {\'e}tiquettes des instances est d{\'e}s{\'e}quilibr{\'e}e. Les performances de ce mod{\`e}le sont mesur{\'e}es {\`a} l{'}aide d{'}exp{\'e}riences men{\'e}es sur les t{\^a}ches de classification de recettes de cuisine de la campagne DEFT 2013 (Grouin et al., 2013).
Language Modeling with a General Second-Order RNN
Different Recurrent Neural Network (RNN) architectures update their state in different manners as the input sequence is processed.
Cooking Up a Neural-based Model for Recipe Classification
In this paper, we propose a neural-based model to address the first task of the DEFT 2013 shared task, with the main challenge of a highly imbalanced dataset, using state-of-the-art embedding approaches and deep architectures.
Inter and Intra Document Attention for Depression Risk Assessment
We take interest in the early assessment of risk for depression in social media users.
Multiplicative Models for Recurrent Language Modeling
Recently, there has been interest in multiplicative recurrent neural networks for language modeling.
Independently Controllable Factors
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation.
SemLinker, a Modular and Open Source Framework for Named Entity Discovery and Linking
This paper presents SemLinker, an open source system that discovers named entities, connects them to a reference knowledge base, and clusters them semantically.
Improving Entity Linking using Surface Form Refinement
The approach extends the surface form coverage of our entity linking system, and rewrites or reformulates misspelled mentions (entities) prior to starting the annotation process.
