Search Results for author:
Found 8 papers, 4 papers with code
Un corpus annoté pour la génération de questions et l’extraction de réponses pour l’enseignement (An annotated corpus for abstractive question generation and extractive answer for education)
Dans cette démonstration, nous présenterons les travaux en cours pour l’annotation d’un nouveau corpus de questions-réponses en langue Française.
Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification
This study is part of the debate on the efficiency of large versus small language models for text classification by prompting. We assess the performance of small language models in zero-shot text classification, challenging the prevailing dominance of large models. Across 15 datasets, our investigation benchmarks language models from 77M to 40B parameters using different architectures and scoring functions.
CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval
Conversational search is a difficult task as it aims at retrieving documents based not only on the current user query but also on the full conversation history.
Continual Learning of Long Topic Sequences in Neural Information Retrieval
In information retrieval (IR) systems, trends and users' interests may change over time, altering either the distribution of requests or contents to be recommended.
Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
In this work, our aim is to provide a structured answer in natural language to a complex information need.
Geomstats: A Python Package for Riemannian Geometry in Machine Learning
We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear manifolds, such as hyperbolic spaces, spaces of symmetric positive definite matrices, Lie groups of transformations, and many more.
From Node Embedding To Community Embedding : A Hyperbolic Approach
Considering the success of hyperbolic representations of graph-structured data in last years, an ongoing challenge is to set up a hyperbolic approach for the community detection problem.
Binary Stochastic Representations for Large Multi-class Classification
Different models based on the notion of binary codes have been proposed to overcome this limitation, achieving in a sublinear inference complexity.
