no code implementations • JEP/TALN/RECITAL 2021 • Diana Nicoleta Popa, William N. Havard, Maximin Coavoux, Eric Gaussier, Laurent Besacier
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.
no code implementations • 28 Jan 2025 • Minghan Li, Eric Gaussier, Guodong Zhou
In recent years, large language models (LLMs) have demonstrated exceptional power in various domains, including information retrieval.
1 code implementation • 23 Nov 2024 • Éloi Zablocki, Valentin Gerard, Amaia Cardiel, Eric Gaussier, Matthieu Cord, Eduardo Valle
We introduce GIFT, a framework for deriving post-hoc, global, interpretable, and faithful textual explanations for vision classifiers.
no code implementations • 9 Nov 2024 • Minghan Li, Eric Gaussier, Juntao Li, Guodong Zhou
Comprehensive experiments on long-document datasets, including TREC 2019 DL, Robust04, and MLDR-zh, show that KeyB2 outperforms baselines like RankLLaMA and KeyB by reducing reranking time and GPU memory usage while enhancing retrieval performance, achieving new SOTA results on TREC 2019 DL with higher NDCG@10 and MAP scores.
no code implementations • 13 Mar 2024 • Minghan Li, Eric Gaussier
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.
1 code implementation • 9 Feb 2024 • Lei Zan, Charles K. Assaad, Emilie Devijver, Eric Gaussier, Ali Aït-Bachir
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.
no code implementations • 23 Oct 2023 • Charles K. Assaad, Emilie Devijver, Eric Gaussier, Gregor Gössler, Anouar Meynaoui
We study the problem of identifiability of the total effect of an intervention from observational time series in the situation, common in practice, where one only has access to abstractions of the true causal graph.
no code implementations • 28 Jul 2023 • Ali Aït-Bachir, Charles K. Assaad, Christophe de Bignicourt, Emilie Devijver, Simon Ferreira, Eric Gaussier, Hosein Mohanna, Lei Zan
Despite its potential benefits, applying causal discovery algorithms on IT monitoring data poses challenges, due to the complexity of the data.
1 code implementation • 14 Jun 2023 • Daria Bystrova, Charles K. Assaad, Julyan Arbel, Emilie Devijver, Eric Gaussier, Wilfried Thuiller
In the second class, a constraint-based strategy is applied to identify a skeleton, which is then oriented using a noise-based strategy.
no code implementations • 13 Dec 2022 • Minghan Li, Eric Gaussier
To address this issue, researchers have resorted to adversarial learning and query generation approaches; both approaches nevertheless resulted in limited improvements.
no code implementations • 19 May 2022 • Charles K. Assaad, Emilie Devijver, Eric Gaussier
This study addresses the problem of learning an extended summary causal graph on time series.
1 code implementation • 18 Nov 2021 • Minghan Li, Diana Nicoleta Popa, Johan Chagnon, Yagmur Gizem Cinar, Eric Gaussier
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.
no code implementations • 21 May 2021 • Charles K. Assaad, Emilie Devijver, Eric Gaussier
This study addresses the problem of learning a summary causal graph on time series with potentially different sampling rates.
1 code implementation • 3 May 2021 • Thibaut Thonet, Yagmur Gizem Cinar, Eric Gaussier, Minghan Li, Jean-Michel Renders
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.
no code implementations • EACL 2021 • Quentin Grail, Julien Perez, Eric Gaussier
Fine-tuning a large language model on downstream tasks has become a commonly adopted process in the Natural Language Processing (NLP) (CITATION).
no code implementations • NeurIPS 2020 • Sami Alkhoury, Emilie Devijver, Marianne Clausel, Myriam Tami, Eric Gaussier, Georges Oppenheim
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.
1 code implementation • CONLL 2020 • Romain Couillet, Yagmur Gizem Cinar, Eric Gaussier, Muhammad Imran
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.
no code implementations • NeurIPS 2020 • Hamid Jalalzai, Pierre Colombo, Chloé Clavel, Eric Gaussier, Giovanna Varni, Emmanuel Vignon, Anne Sabourin
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
no code implementations • 26 Feb 2020 • Xuhui Fan, Eric Gaussier
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.
no code implementations • 25 Sep 2019 • Hamid Jalalzai, Pierre Colombo, Chloé Clavel, Eric Gaussier, Giovanna Varni, Emmanuel Vignon, Anne Sabourin
The dominant approaches to sentence representation in natural language rely on learning embeddings on massive corpuses.
no code implementations • 25 Sep 2019 • Quentin Grail, Julien Perez, Eric Gaussier
The purpose of the reading module is to produce a question-aware representation of the document.
no code implementations • JEPTALNRECITAL 2019 • Hamid Mirisaee, Eric Gaussier, Cedric Lagnier, Agnes Guerraz
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.
no code implementations • WS 2018 • Shubham Agarwal, Marc Dymetman, Eric Gaussier
This paper describes our submission to the E2E NLG Challenge.
no code implementations • 27 Oct 2018 • Myriam Tami, Marianne Clausel, Emilie Devijver, Adrien Dulac, Eric Gaussier, Stefan Janaqi, Meriam Chebre
Tree-based ensemble methods, as Random Forests and Gradient Boosted Trees, have been successfully used for regression in many applications and research studies.
1 code implementation • 26 Jun 2018 • Maziar Moradi Fard, Thibaut Thonet, Eric Gaussier
We study in this paper the problem of jointly clustering and learning representations.
1 code implementation • ACL 2017 • Hesam Amoualian, Wei Lu, Eric Gaussier, Georgios Balikas, Massih R. Amini, Marianne Clausel
This paper presents an LDA-based model that generates topically coherent segments within documents by jointly segmenting documents and assigning topics to their words.
no code implementations • 29 Mar 2017 • Yagmur G. Cinar, Hamid Mirisaee, Parantapa Goswami, Eric Gaussier, Ali Ait-Bachir, Vadim Strijov
We propose here an extended attention model for sequence-to-sequence recurrent neural networks (RNNs) designed to capture (pseudo-)periods in time series.
1 code implementation • COLING 2016 • Georgios Balikas, Hesam Amoualian, Marianne Clausel, Eric Gaussier, Massih R. Amini
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.
no code implementations • COLING 2016 • Raghav Goyal, Marc Dymetman, Eric Gaussier
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.
no code implementations • 30 Mar 2015 • Ioannis Partalas, Aris Kosmopoulos, Nicolas Baskiotis, Thierry Artieres, George Paliouras, Eric Gaussier, Ion Androutsopoulos, Massih-Reza Amini, Patrick Galinari
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).
no code implementations • 10 Sep 2014 • Abdelkader El Mahdaouy, Saïd EL Alaoui Ouatik, Eric Gaussier
Automatic Multi-Word Term (MWT) extraction is a very important issue to many applications, such as information retrieval, question answering, and text categorization.
no code implementations • NeurIPS 2013 • Rohit Babbar, Ioannis Partalas, Eric Gaussier, Massih R. Amini
We study in this paper flat and hierarchical classification strategies in the context of large-scale taxonomies.
2 code implementations • 28 Jun 2013 • Aris Kosmopoulos, Ioannis Partalas, Eric Gaussier, Georgios Paliouras, Ion Androutsopoulos
Hierarchical classification addresses the problem of classifying items into a hierarchy of classes.