38 citations · 93 across the 19 of their papers we have counts for
23 papers
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
Alexandre Ramé, Guillaume Couairon, Mustafa Shukor +4
Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further a…
Dynamic Named Entity Recognition
Tristan Luiggi, Laure Soulier, Vincent Guigue +2
Named Entity Recognition (NER) is a challenging and widely studied task that involves detecting and typing entities in text. So far,NER still approaches entity typing as a task of…
CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval
Nam Le Hai, Thomas Gerald, Thibault Formal +3
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. Most of the previou…
Building a Subspace of Policies for Scalable Continual Learning
Jean-Baptiste Gaya, Thang Doan, Lucas Caccia +3
The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to lea…
Interactive Query Clarification and Refinement via User Simulation
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. Multiple approaches have been propose…
State of the Art of User Simulation approaches for conversational information retrieval
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…
Continual Learning of Long Topic Sequences in Neural Information Retrieval
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. Since neural ra…
Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
Hanane Djeddal, Thomas Gerald, Laure Soulier +2
In this work, our aim is to provide a structured answer in natural language to a complex information need. Particularly, we envision using generative models from the perspective of…
Learning a subspace of policies for online adaptation in Reinforcement Learning
Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer
Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments…
Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation
Clément Rebuffel, Thomas Scialom, Laure Soulier +5
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.…
Controlling Hallucinations at Word Level in Data-to-Text Generation
Clément Rebuffel, Marco Roberti, Laure Soulier +3
Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field has been recently boos…
Studying Catastrophic Forgetting in Neural Ranking Models
Jesus Lovon-Melgarejo, Laure Soulier, Karen Pinel-Sauvagnat +1
Several deep neural ranking models have been proposed in the recent IR literature. While their transferability to one target domain held by a dataset has been widely addressed usin…
PARENTing via Model-Agnostic Reinforcement Learning to Correct Pathological Behaviors in Data-to-Text Generation
Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten +1
In language generation models conditioned by structured data, the classical training via maximum likelihood almost always leads models to pick up on dataset divergence (i.e., hallu…
Incorporating Visual Semantics into Sentence Representations within a Grounded Space
Patrick Bordes, Eloi Zablocki, Laure Soulier +2
Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same represent…
Conversational Search for Learning Technologies
Sharon Oviatt, Laure Soulier
Conversational search is based on a user-system cooperation with the objective to solve an information-seeking task. In this report, we discuss the implication of such cooperation…
A Hierarchical Model for Data-to-Text Generation
Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten +1
Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elemen…
Context-Aware Zero-Shot Learning for Object Recognition
Eloi Zablocki, Patrick Bordes, Benjamin Piwowarski +2
Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only…
A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems
Wafa Aissa, Laure Soulier, Ludovic Denoyer
Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keyword-based…
Images & Recipes: Retrieval in the cooking context
Micael Carvalho, Rémi Cadène, David Picard +2
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. In this…
Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings
Micael Carvalho, Rémi Cadène, David Picard +3
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…
Learning Multi-Modal Word Representation Grounded in Visual Context
Éloi Zablocki, Benjamin Piwowarski, Laure Soulier +1
Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in lar…
DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents
Gia-Hung Nguyen, Laure Soulier, Lynda Tamine +1
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 t…
Toward a Deep Neural Approach for Knowledge-Based IR
Gia-Hung Nguyen, Lynda Tamine, Laure Soulier +1
This paper tackles the problem of the semantic gap between a document and a query within an ad-hoc information retrieval task. In this context, knowledge bases (KBs) have already b…