RLRémi Lebret

Rémi Lebret

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Rémi Lebret has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Stance Detection on Social Media with Fine-Tuned Large Language Models

    by İlker Gül, Rémi Lebret, Karl Aberer

    Stance detection, a key task in natural language processing, determines an author's viewpoint based on textual analysis. This study evaluates the evolution of stance detection methods, transitioning from early machine learning approaches to the groundbreaking BERT model, and eventually to modern Large Language Models (LLMs) such as ChatGPT, LLaMa-2, and Mistral-7B. While ChatGPT's closed-source nature and associated costs present challenges, the open-source models like LLaMa-2 and Mistral-7B offers an encouraging alternative. Initially, our research focused on fine-tuning ChatGPT, LLaMa-2, and Mistral-7B using several publicly available datasets. Subsequently, to provide a comprehensive comparison, we assess the performance of these models in zero-shot and few-shot learning scenarios. The results underscore the exceptional ability of LLMs in accurately detecting stance, with all tested models surpassing existing benchmarks. Notably, LLaMa-2 and Mistral-7B demonstrate remarkable efficiency and potential for stance detection, despite their smaller sizes compared to ChatGPT. This study emphasizes the potential of LLMs in stance detection and calls for more extensive research in this field.


  • Open Access

    AdaGrid: Adaptive Grid Search for Link Prediction Training Objective

    by Tim Poštuvan, Jiaxuan You, Mohammadreza Banaei, Rémi Lebret, Jure Leskovec

    One of the most important factors that contribute to the success of a machine learning model is a good training objective. Training objective crucially influences the model's performance and generalization capabilities. This paper specifically focuses on graph neural network training objective for link prediction, which has not been explored in the existing literature. Here, the training objective includes, among others, a negative sampling strategy, and various hyperparameters, such as edge message ratio which controls how training edges are used. Commonly, these hyperparameters are fine-tuned by complete grid search, which is very time-consuming and model-dependent. To mitigate these limitations, we propose Adaptive Grid Search (AdaGrid), which dynamically adjusts the edge message ratio during training. It is model agnostic and highly scalable with a fully customizable computational budget. Through extensive experiments, we show that AdaGrid can boost the performance of the models up to $1.9\%$ while being nine times more time-efficient than a complete search. Overall, AdaGrid represents an effective automated algorithm for designing machine learning training objectives.


  • Open Access

    Direction is what you need: Improving Word Embedding Compression in Large Language Models

    by Klaudia Bałazy, Mohammadreza Banaei, Rémi Lebret, Jacek Tabor, Karl Aberer

    The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression of these models to improve their inference time and memory footprint. This paper presents a novel loss objective to compress token embeddings in the Transformer-based models by leveraging an AutoEncoder architecture. More specifically, we emphasize the importance of the direction of compressed embeddings with respect to original uncompressed embeddings. The proposed method is task-agnostic and does not require further language modeling pre-training. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity. Moreover, we evaluate our proposed approach over SQuAD v1.1 dataset and several downstream tasks from the GLUE benchmark, where we also outperform the baseline in most scenarios. Our code is public.

  • Open Access

    Upgrading the Newsroom: An Automated Image Selection System for News Articles

    by Fangyu Liu, Rémi Lebret, Didier Orel, Philippe Sordet, Karl Aberer

    We propose an automated image selection system to assist photo editors in selecting suitable images for news articles. The system fuses multiple textual sources extracted from news articles and accepts multilingual inputs. It is equipped with char-level word embeddings to help both modeling morphologically rich languages, e.g. German, and transferring knowledge across nearby languages. The text encoder adopts a hierarchical self-attention mechanism to attend more to both keywords within a piece of text and informative components of a news article. We extensively experiment with our system on a large-scale text-image database containing multimodal multilingual news articles collected from Swiss local news media websites. The system is compared with multiple baselines with ablation studies and is shown to beat existing text-image retrieval methods in a weakly-supervised learning setting. Besides, we also offer insights on the advantage of using multiple textual sources and multilingual data.

  • Open Access

    Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task

    by Alireza Mohammadshahi, Remi Lebret, Karl Aberer

    In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.

  • Open Access

    Weakly Supervised Active Learning with Cluster Annotation

    by Fábio Perez, Rémi Lebret, Karl Aberer

    In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples with the cost of a small label error. Our experiments show that the proposed framework requires 82% and 87% less human interactions for CIFAR-10 and EuroSAT datasets respectively when compared with the fully-supervised training while maintaining similar performance on the test set.

  • Open Access

    Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task

    by Alireza Mohammadshahi, Rémi Lebret, Karl Aberer

    Alireza Mohammadshahi, Rémi Lebret, Karl Aberer. Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER). 2019.


  • Open Access

    Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task

    by Alireza Mohammadshahi, Rémi Lebret, Karl Aberer

    Alireza Mohammadshahi, Rémi Lebret, Karl Aberer. Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN). 2019.


  • Open Access

    Multimodal Classification for Analysing Social Media

    by Chi Thang Duong, Remi Lebret, Karl Aberer

    Classification of social media data is an important approach in understanding user behavior on the Web. Although information on social media can be of different modalities such as texts, images, audio or videos, traditional approaches in classification usually leverage only one prominent modality. Techniques that are able to leverage multiple modalities are often complex and susceptible to the absence of some modalities. In this paper, we present simple models that combine information from different modalities to classify social media content and are able to handle the above problems with existing techniques. Our models combine information from different modalities using a pooling layer and an auxiliary learning task is used to learn a common feature space. We demonstrate the performance of our models and their robustness to the missing of some modalities in the emotion classification domain. Our approaches, although being simple, can not only achieve significantly higher accuracies than traditional fusion approaches but also have comparable results when only one modality is available.