Search Results for author:
Found 100 papers, 48 papers with code
FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation
While traditional natural language generation metrics are fast, they are not very reliable.
Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Models
Graph generation has emerged as a crucial task in machine learning, with significant challenges in generating graphs that accurately reflect specific properties.
Assessing the Efficacy of Heuristic-Based Address Clustering for Bitcoin
This process often employs heuristics grounded in the practices and behaviors of these entities.
A Simple and Yet Fairly Effective Defense for Graph Neural Networks
Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results.
Graph Neural Machine: A New Model for Learning with Tabular Data
We then propose a new machine learning model for tabular data, the so-called Graph Neural Machine (GNM), which replaces the MLP's directed acyclic graph with a nearly complete graph and which employs a synchronous message passing scheme.
FREDSum: A Dialogue Summarization Corpus for French Political Debates
In this paper, we present a dataset of French political debates for the purpose of enhancing resources for multi-lingual dialogue summarization.
Heuristics for Detecting CoinJoin Transactions on the Bitcoin Blockchain
This study delves deeply into the open-source implementations of these protocols, aiming to develop refined heuristics for identifying their transactions on the blockchain.
Automatic Analysis of Substantiation in Scientific Peer Reviews
With the increasing amount of problematic peer reviews in top AI conferences, the community is urgently in need of automatic quality control measures.
The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text
This study investigates the consequences of training large language models (LLMs) on synthetic data generated by their predecessors, an increasingly prevalent practice aimed at addressing the limited supply of human-generated training data.
Interpretable Graph Neural Networks for Tabular Data
Data in tabular format is frequently occurring in real-world applications.
Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series
We evaluate TPCNN on both interpolation and classification tasks involving real-world irregularly sampled multivariate time series datasets.
Adaptive Collaborative Filtering with Personalized Time Decay Functions for Financial Product Recommendation
Classical recommender systems often assume that historical data are stationary and fail to account for the dynamic nature of user preferences, limiting their ability to provide reliable recommendations in time-sensitive settings.
TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
Time series forecasting lies at the core of important real-world applications in many fields of science and engineering.
Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers
The complex nature of big biological systems pushed some scientists to classify its understanding under the inconceivable missions.
Supervised Attention Using Homophily in Graph Neural Networks
Among the different variants of graph neural networks, graph attention networks (GATs) have been applied with great success to different tasks.
Path Neural Networks: Expressive and Accurate Graph Neural Networks
We derive three different variants of the PathNN model that aggregate single shortest paths, all shortest paths and all simple paths of length up to K. We prove that two of these variants are strictly more powerful than the 1-WL algorithm, and we experimentally validate our theoretical results.
Ranked #7 on
Graph Classification
on Peptides-func
What Do GNNs Actually Learn? Towards Understanding their Representations
In recent years, graph neural networks (GNNs) have achieved great success in the field of graph representation learning.
GreekBART: The First Pretrained Greek Sequence-to-Sequence Model
In addition, we examine its performance on two NLG tasks from GreekSUM, a newly introduced summarization dataset for the Greek language.
Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia
To the best of our knowledge, there is no prior work exploiting a NAS approach and these fusion methods in the task of dementia detection from spontaneous speech.
Explainable Multilayer Graph Neural Network for Cancer Gene Prediction
Unlike conventional graph learning on a single biological network, EMGNN uses a multilayered graph neural network to learn from multiple biological networks for accurate cancer gene prediction.
New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction
It is still unclear to what extent one can improve CD with GAE and VGAE, especially in the absence of node features.
Improving Graph Neural Networks at Scale: Combining Approximate PageRank and CoreRank
Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph structures.
Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
In recent years, graph neural networks (GNNs) have emerged as a promising tool for solving machine learning problems on graphs.
Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency
Due to this lack of well-defined formulation, a large number of popular abstractive summarization datasets are constructed in a manner that neither guarantees validity nor meets one of the most essential criteria of summarization: factual consistency.
DATScore: Evaluating Translation with Data Augmented Translations
The rapid development of large pretrained language models has revolutionized not only the field of Natural Language Generation (NLG) but also its evaluation.
Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization
In this paper, we propose a novel unsupervised method based on hierarchical clustering and invariant information clustering (IIC).
Abstractive Meeting Summarization: A Survey
A system that could reliably identify and sum up the most important points of a conversation would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls.
Abstractive Dialogue Summarization
Abstractive Text Summarization
+2
Time Series Forecasting Models Copy the Past: How to Mitigate
Recently neural network architectures have been widely applied to the problem of time series forecasting.
DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is fundamental work.
Image Keypoint Matching using Graph Neural Networks
Image matching is a key component of many tasks in computer vision and its main objective is to find correspondences between features extracted from different natural images.
Political Communities on Twitter: Case Study of the 2022 French Presidential Election
We perform community detection on a retweet graph of users and propose an in-depth analysis of the stance of each community.
Graph Ordering Attention Networks
The GOAT model demonstrates its increased performance in modeling graph metrics that capture complex information, such as the betweenness centrality and the effective size of a node.
AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization
Like most natural language understanding and generation tasks, state-of-the-art models for summarization are transformer-based sequence-to-sequence architectures that are pretrained on large corpora.
Abstractive Text Summarization
Natural Language Understanding
Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as powerful methods for link prediction.
NLP Research and Resources at DaSciM, Ecole Polytechnique
DaSciM (Data Science and Mining) part of LIX at Ecole Polytechnique, established in 2013 and since then producing research results in the area of large scale data analysis via methods of machine and deep learning.
FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation
While traditional natural language generation metrics are fast, they are not very reliable.
Permute Me Softly: Learning Soft Permutations for Graph Representations
In this paper, we propose a new graph neural network model, so-called $\pi$-GNN which learns a "soft" permutation (i. e., doubly stochastic) matrix for each graph, and thus projects all graphs into a common vector space.
JuriBERT: A Masked-Language Model Adaptation for French Legal Text
Language models have proven to be very useful when adapted to specific domains.
Geometric Random Walk Graph Neural Networks via Implicit Layers
The proposed model retains the transparency of Random Walk Graph Neural Networks since its first layer also consists of a number of trainable ``hidden graphs'' which are compared against the input graphs using the geometric random walk kernel.
BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets
We make our model publicly available in the transformers library with the aim of promoting future research in analytic tasks for French tweets.
Node Feature Kernels Increase Graph Convolutional Network Robustness
The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance.
Sparsifying the Update Step in Graph Neural Networks
In this paper we conduct a structured, empirical study of the effect of sparsification on the trainable part of MPNNs known as the Update step.
Maximizing Influence with Graph Neural Networks
Finding the seed set that maximizes the influence spread over a network is a well-known NP-hard problem.
Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
In this paper, we model this cold start similar artists ranking problem as a link prediction task in a directed and attributed graph, connecting artists to their top-k most similar neighbors and incorporating side musical information.
Graph-based Neural Architecture Search with Operation Embeddings
Neural Architecture Search (NAS) has recently gained increased attention, as a class of approaches that automatically searches in an input space of network architectures.
Evaluation Of Word Embeddings From Large-Scale French Web Content
Adding that pretrained word vectors on huge text corpus achieved high performance in many different NLP tasks.
Ego-based Entropy Measures for Structural Representations on Graphs
Machine learning on graph-structured data has attracted high research interest due to the emergence of Graph Neural Networks (GNNs).
How COVID-19 Is Changing Our Language : Detecting Semantic Shift in Twitter Word Embeddings
We employ an alignment-based approach to compare these embeddings with a general-purpose Twitter embedding unrelated to COVID-19.
Learning Parametrised Graph Shift Operators
In many domains data is currently represented as graphs and therefore, the graph representation of this data becomes increasingly important in machine learning.
An Empirical Study of the Expressiveness of Graph Kernels and Graph Neural Networks
Graph neural networks and graph kernels have achieved great success in solving machine learning problems on graphs.
Analysing the Update step in Graph Neural Networks via Sparsification
In recent years, Message-Passing Neural Networks (MPNNs), the most prominent Graph Neural Network (GNN) framework, have celebrated much success in the analysis of graph-structured data.
Random Walk Graph Neural Networks
The first layer of the model consists of a number of trainable ``hidden graphs'' which are compared against the input graphs using a random walk kernel to produce graph representations.
BARThez: a Skilled Pretrained French Sequence-to-Sequence Model
We show BARThez to be very competitive with state-of-the-art BERT-based French language models such as CamemBERT and FlauBERT.
Ranked #1 on
Text Summarization
on OrangeSum
(using extra training data)
Transfer Graph Neural Networks for Pandemic Forecasting
Furthermore, to account for the limited amount of training data, we capitalize on the pandemic's asynchronous outbreaks across countries and use a model-agnostic meta-learning based method to transfer knowledge from one country's model to another's.
Predicting conversions in display advertising based on URL embeddings
Online display advertising is growing rapidly in recent years thanks to the automation of the ad buying process.
Performance in the Courtroom: Automated Processing and Visualization of Appeal Court Decisions in France
Artificial Intelligence techniques are already popular and important in the legal domain.
Hcore-Init: Neural Network Initialization based on Graph Degeneracy
As a multipartite graph is a combination of bipartite graphs, that are in turn the incidence graphs of hypergraphs, we design k-hypercore decomposition, the hypergraph analogue of k-core degeneracy.
Speaker-change Aware CRF for Dialogue Act Classification
CRF models the conditional probability of the target DA label sequence given the input utterance sequence.
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings
A valuable by-product of our method is the ability to sample, at no extra cost, sentences containing different senses of a given word.
EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
Then, we employ a generative model which predicts the topology of the graph at the next time step and constructs a graph instance that corresponds to that topology.
Ego-based Entropy Measures for Structural Representations
Moreover, on graph classification tasks, we suggest the utilization of the generated structural embeddings for the transformation of an attributed graph structure into a set of augmented node attributes.
FastGAE: Scalable Graph Autoencoders with Stochastic Subgraph Decoding
Graph autoencoders (AE) and variational autoencoders (VAE) are powerful node embedding methods, but suffer from scalability issues.
Simple and Effective Graph Autoencoders with One-Hop Linear Models
Over the last few years, graph autoencoders (AE) and variational autoencoders (VAE) emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering.
An Ensemble Method for Producing Word Representations focusing on the Greek Language
In this paper we present a new ensemble method, Continuous Bag-of-Skip-grams (CBOS), that produces high-quality word representations putting emphasis on the modern Greek language.
Scalable graph-based method for individual named entity identification
In this paper, we consider the named entity linking (NEL) problem.
Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering.
Message Passing Attention Networks for Document Understanding
In this paper, we represent documents as word co-occurrence networks and propose an application of the message passing framework to NLP, the Message Passing Attention network for Document understanding (MPAD).
Ranked #1 on
Multi-Modal Document Classification
on Reuters-21578
document understanding
Multi-Modal Document Classification
+2
Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding
The Hierarchical Attention Network (HAN) has made great strides, but it suffers a major limitation: at level 1, each sentence is encoded in complete isolation.
k-hop Graph Neural Networks
We show that the proposed architecture can identify fundamental graph properties.
Gravity-Inspired Graph Autoencoders for Directed Link Prediction
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods.
Graph Kernels: A Survey
Graph kernels have attracted a lot of attention during the last decade, and have evolved into a rapidly developing branch of learning on structured data.
Ranked #11 on
Graph Classification
on NCI1
Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding
Abstractive community detection is an important spoken language understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly summarized by a common abstractive sentence.
Multi-task Learning for Influence Estimation and Maximization
The first part of our methodology is a multi-task neural network that learns embeddings of nodes that initiate cascades (influencer vectors) and embeddings of nodes that participate in them (susceptible vectors).
Evaluation of Greek Word Embeddings
Since word embeddings have been the most popular input for many NLP tasks, evaluating their quality is of critical importance.
Randomised Bayesian Least-Squares Policy Iteration
We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies.
Rep the Set: Neural Networks for Learning Set Representations
In several domains, data objects can be decomposed into sets of simpler objects.
Ranked #1 on
Document Classification
on Twitter
A Degeneracy Framework for Scalable Graph Autoencoders
In this paper, we present a general framework to scale graph autoencoders (AE) and graph variational autoencoders (VAE).
Word Embeddings from Large-Scale Greek Web Content
Word embeddings are undoubtedly very useful components in many NLP tasks.
Message Passing Graph Kernels
The first component is a kernel between vertices, while the second component is a kernel between graphs.
Perturb and Combine to Identify Influential Spreaders in Real-World Networks
Some of the most effective influential spreader detection algorithms are unstable to small perturbations of the network structure.
Orthogonal Matching Pursuit for Text Classification
In text classification, the problem of overfitting arises due to the high dimensionality, making regularization essential.
GraKeL: A Graph Kernel Library in Python
The problem of accurately measuring the similarity between graphs is at the core of many applications in a variety of disciplines.
Fusing Document, Collection and Label Graph-based Representations with Word Embeddings for Text Classification
Contrary to the traditional Bag-of-Words approach, we consider the Graph-of-Words(GoW) model in which each document is represented by a graph that encodes relationships between the different terms.
Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization
We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations.
Ranked #1 on
Meeting Summarization
on ICSI Meeting Corpus
Abstractive Dialogue Summarization
Abstractive Text Summarization
+6
Kernel Graph Convolutional Neural Nets
Graph kernels have been successfully applied to many graph classification problems.
Kernel Graph Convolutional Neural Networks
Graph kernels have been successfully applied to many graph classification problems.
Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization
We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research.
Shortest-Path Graph Kernels for Document Similarity
In this paper, we present a novel document similarity measure based on the definition of a graph kernel between pairs of documents.
Graph Classification with 2D Convolutional Neural Networks
Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations.
Ranked #3 on
Graph Classification
on RE-M12K
Adaptive Submodular Influence Maximization with Myopic Feedback
This paper examines the problem of adaptive influence maximization in social networks.
Social and Information Networks
Real-Time Keyword Extraction from Conversations
We introduce a novel method to extract keywords from meeting speech in real-time.
Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization
Recently, there has been a lot of activity in learning distributed representations of words in vector spaces.
Word Embeddings for the Construction Domain
Our vectors were obtained by running word2vec on an 11M-word corpus that we created from scratch by leveraging freely-accessible online sources of construction-related text.
Text Relatedness Based on a Word Thesaurus
Without doubt, a measure of relatedness between text segments must take into account both the lexical and the semantic relatedness between words.
Clustering and Community Detection in Directed Networks: A Survey
Networks (or graphs) appear as dominant structures in diverse domains, including sociology, biology, neuroscience and computer science.
