Search Results for author:
Found 30 papers, 9 papers with code
Contribution d’informations syntaxiques aux capacités de généralisation compositionelle des modèles seq2seq convolutifs (Assessing the Contribution of Syntactic Information for Compositional Generalization of seq2seq Convolutional Networks)
Le jeu de données SCAN, constitué d’un ensemble de commandes en langage naturel associées à des séquences d’action, a été spécifiquement conçu pour évaluer les capacités des réseaux de neurones à apprendre ce type de généralisation compositionnelle.
Domain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labeling
Experiments on standard dense retrieval and conversational dense retrieval models both demonstrate improvements on baseline models when they are fine-tuned on the pseudo-relevance labeled data.
On the Fly Detection of Root Causes from Observed Data with Application to IT Systems
This paper introduces a new structural causal model tailored for representing threshold-based IT systems and presents a new algorithm designed to rapidly detect root causes of anomalies in such systems.
Identifiability of total effects from abstractions of time series causal graphs
We study the problem of identifiability of the total effect of an intervention from observational time series only given an abstraction of the causal graph of the system.
Case Studies of Causal Discovery from IT Monitoring Time Series
Despite its potential benefits, applying causal discovery algorithms on IT monitoring data poses challenges, due to the complexity of the data.
Hybrids of Constraint-based and Noise-based Algorithms for Causal Discovery from Time Series
Constraint-based and noise-based methods have been proposed to discover summary causal graphs from observational time series under strong assumptions which can be violated or impossible to verify in real applications.
Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling
To address this issue, researchers have resorted to adversarial learning and query generation approaches; both approaches nevertheless resulted in limited improvements.
Inferring extended summary causal graphs from observational time series
This study addresses the problem of learning an extended summary causal graph on time series.
The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval
On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness.
Entropy-based Discovery of Summary Causal Graphs in Time Series
This study addresses the problem of learning a summary causal graph on time series with potentially different sampling rates.
SmoothI: Smooth Rank Indicators for Differentiable IR Metrics
To address this shortcoming, we propose SmoothI, a smooth approximation of rank indicators that serves as a basic building block to devise differentiable approximations of IR metrics.
Globalizing BERT-based Transformer Architectures for Long Document Summarization
Fine-tuning a large language model on downstream tasks has become a commonly adopted process in the Natural Language Processing (NLP) (CITATION).
Smooth And Consistent Probabilistic Regression Trees
We propose here a generalization of regression trees, referred to as Probabilistic Regression (PR) trees, that adapt to the smoothness of the prediction function relating input and output variables while preserving the interpretability of the prediction and being robust to noise.
Word Representations Concentrate and This is Good News!
This article establishes that, unlike the legacy tf*idf representation, recent natural language representations (word embedding vectors) tend to exhibit a so-called \textit{concentration of measure phenomenon}, in the sense that, as the representation size $p$ and database size $n$ are both large, their behavior is similar to that of large dimensional Gaussian random vectors.
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation
The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation.
Ranked #3 on
Sentiment Analysis
on Yelp Binary classification
Supervised Categorical Metric Learning with Schatten p-Norms
In this paper, we propose a method, called CPML for \emph{categorical projected metric learning}, that tries to efficiently~(i. e. less computational time and better prediction accuracy) address the problem of metric learning in categorical data.
Latent Question Reformulation and Information Accumulation for Multi-Hop Machine Reading
The purpose of the reading module is to produce a question-aware representation of the document.
Terminology-based Text Embedding for Computing Document Similarities on Technical Content
We propose in this paper a new, hybrid document embedding approach in order to address the problem of document similarities with respect to the technical content.
Char2char Generation with Reranking for the E2E NLG Challenge
This paper describes our submission to the E2E NLG Challenge.
Uncertain Trees: Dealing with Uncertain Inputs in Regression Trees
Tree-based ensemble methods, as Random Forests and Gradient Boosted Trees, have been successfully used for regression in many applications and research studies.
Deep $k$-Means: Jointly clustering with $k$-Means and learning representations
We study in this paper the problem of jointly clustering and learning representations.
Topical Coherence in LDA-based Models through Induced Segmentation
This paper presents an LDA-based model that generates topically coherent segments within documents by jointly segmenting documents and assigning topics to their words.
Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
We propose here an extended attention model for sequence-to-sequence recurrent neural networks (RNNs) designed to capture (pseudo-)periods in time series.
Natural Language Generation through Character-based RNNs with Finite-state Prior Knowledge
Recently Wen et al. (2015) have proposed a Recurrent Neural Network (RNN) approach to the generation of utterances from dialog acts, and shown that although their model requires less effort to develop than a rule-based system, it is able to improve certain aspects of the utterances, in particular their naturalness.
Modeling topic dependencies in semantically coherent text spans with copulas
The exchangeability assumption in topic models like Latent Dirichlet Allocation (LDA) often results in inferring inconsistent topics for the words of text spans like noun-phrases, which are usually expected to be topically coherent.
LSHTC: A Benchmark for Large-Scale Text Classification
LSHTC is a series of challenges which aims to assess the performance of classification systems in large-scale classification in a a large number of classes (up to hundreds of thousands).
A Study of Association Measures and their Combination for Arabic MWT Extraction
Automatic Multi-Word Term (MWT) extraction is a very important issue to many applications, such as information retrieval, question answering, and text categorization.
On Flat versus Hierarchical Classification in Large-Scale Taxonomies
We study in this paper flat and hierarchical classification strategies in the context of large-scale taxonomies.
Evaluation Measures for Hierarchical Classification: a unified view and novel approaches
Hierarchical classification addresses the problem of classifying items into a hierarchy of classes.
