1 code implementation • 24 Apr 2024 • Folco Bertini Baldassini, Mustafa Shukor, Matthieu Cord, Laure Soulier, Benjamin Piwowarski
Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples.
no code implementations • 26 Feb 2024 • Pierre Erbacher, Jian-Yun Nie, Philippe Preux, Laure Soulier
Conversational systems have made significant progress in generating natural language responses.
1 code implementation • 31 Jan 2024 • Florian Le Bronnec, Song Duong, Mathieu Ravaut, Alexandre Allauzen, Nancy F. Chen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari
State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies.
no code implementations • 21 Jan 2024 • Mathias Vast, Yuxuan Zong, Basile Van Cooten, Benjamin Piwowarski, Laure Soulier
In Information Retrieval, and more generally in Natural Language Processing, adapting models to specific domains is conducted through fine-tuning.
no code implementations • 3 Jan 2024 • Pierre Erbacher, Louis Falissar, Vincent Guigue, Laure Soulier
Our model directly provides answers for $78. 2\%$ of the known queries and opts to search for $77. 2\%$ of the unknown ones.
no code implementations • 10 Nov 2023 • Pierre Erbacher, Jian-Yun Nie, Philippe Preux, Laure Soulier
The only two datasets known to us that contain both document relevance judgments and the associated clarification interactions are Qulac and ClariQ.
no code implementations • 5 Nov 2023 • Pierre Erbacher, Laure Soulier
In this paper, we introduce CIRCLE, a generative model for multi-turn query Clarifications wIth ReinforCement LEarning that leverages multi-turn interactions through a user simulation framework.
no code implementations • 24 Oct 2023 • Louis Falissard, Vincent Guigue, Laure Soulier
We show in this paper that "Parameter Efficient Fine-Tuning" (PEFT) methods, however, are perfectly compatible with this original approach, and propose to learn entire simplex of continuous prefixes.
1 code implementation • 16 Feb 2023 • Tristan Luiggi, Laure Soulier, Vincent Guigue, Siwar Jendoubi, Aurélien Baelde
Named Entity Recognition (NER) is a challenging and widely studied task that involves detecting and typing entities in text.
no code implementations • 11 Jan 2023 • Nam Le Hai, Thomas Gerald, Thibault Formal, Jian-Yun Nie, Benjamin Piwowarski, Laure Soulier
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.
1 code implementation • 18 Nov 2022 • Jean-Baptiste Gaya, Thang Doan, Lucas Caccia, Laure Soulier, Ludovic Denoyer, Roberta Raileanu
We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of tasks.
no code implementations • 31 May 2022 • Pierre Erbacher, Ludovic Denoyer, Laure Soulier
When users initiate search sessions, their queries are often unclear or might lack of context; this resulting in inefficient document ranking.
1 code implementation • 10 Jan 2022 • Thomas Gerald, Laure Soulier
In information retrieval (IR) systems, trends and users' interests may change over time, altering either the distribution of requests or contents to be recommended.
no code implementations • 10 Jan 2022 • Pierre Erbacher, Laure Soulier, Ludovic Denoyer
Conversational Information Retrieval (CIR) is an emerging field of Information Retrieval (IR) at the intersection of interactive IR and dialogue systems for open domain information needs.
1 code implementation • 8 Dec 2021 • Hanane Djeddal, Thomas Gerald, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine
In this work, our aim is to provide a structured answer in natural language to a complex information need.
1 code implementation • ICLR 2022 • Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer
There is a need to develop RL methods that generalize well to variations of the training conditions.
2 code implementations • EMNLP 2021 • Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano, Geoffrey Scoutheeten, Patrick Gallinari
QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.
1 code implementation • 4 Feb 2021 • Clément Rebuffel, Marco Roberti, Laure Soulier, Geoffrey Scoutheeten, Rossella Cancelliere, Patrick Gallinari
Specifically, we propose a Multi-Branch Decoder which is able to leverage word-level labels to learn the relevant parts of each training instance.
Ranked #3 on Table-to-Text Generation on WikiBio
1 code implementation • 18 Jan 2021 • Jesus Lovon-Melgarejo, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine
Several deep neural ranking models have been proposed in the recent IR literature.
1 code implementation • INLG (ACL) 2020 • Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten, Patrick Gallinari
Evaluations on the widely used WikiBIO and WebNLG benchmarks demonstrate the effectiveness of this framework compared to state-of-the-art models.
no code implementations • IJCNLP 2019 • Patrick Bordes, Eloi Zablocki, Laure Soulier, Benjamin Piwowarski, Patrick Gallinari
To overcome this limitation, we propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space.
no code implementations • 9 Jan 2020 • Sharon Oviatt, Laure Soulier
Conversational search is based on a user-system cooperation with the objective to solve an information-seeking task.
1 code implementation • 20 Dec 2019 • Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten, Patrick Gallinari
This however loses most of the structure contained in the data.
no code implementations • 24 Apr 2019 • Eloi Zablocki, Patrick Bordes, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari
Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations.
no code implementations • WS 2018 • Wafa Aissa, Laure Soulier, Ludovic Denoyer
Search-oriented conversational systems rely on information needs expressed in natural language (NL).
1 code implementation • 2 May 2018 • Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Matthieu Cord
Recent advances in the machine learning community allowed different use cases to emerge, as its association to domains like cooking which created the computational cuisine.
1 code implementation • 30 Apr 2018 • Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Nicolas Thome, Matthieu Cord
Designing powerful tools that support cooking activities has rapidly gained popularity due to the massive amounts of available data, as well as recent advances in machine learning that are capable of analyzing them.
Ranked #9 on Cross-Modal Retrieval on Recipe1M
no code implementations • 9 Nov 2017 • Éloi Zablocki, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari
Representing the semantics of words is a long-standing problem for the natural language processing community.
no code implementations • 15 Jun 2017 • Gia-Hung Nguyen, Laure Soulier, Lynda Tamine, Nathalie Bricon-Souf
The state-of-the-art solutions to the vocabulary mismatch in information retrieval (IR) mainly aim at leveraging either the relational semantics provided by external resources or the distributional semantics, recently investigated by deep neural approaches.
no code implementations • 23 Jun 2016 • Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf
With this in mind, we argue that embedding KBs within deep neural architectures supporting documentquery matching would give rise to fine-grained latent representations of both words and their semantic relations.