Publications associées à Disambiguating Discourse Connectives for Statistical Machine Translation

Publications associées (29)

Regularization Techniques for Low-Resource Machine Translation

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

EPFL2023

Dense Image-based Predictions for Comics Analysis

Deblina Bhattacharjee

Dense image-based prediction methods have advanced tremendously in recent years. Their remarkable development has been possible due to the ample availability of real-world imagery. While these methods work well on photographs, their abilities do not genera ...

EPFL2023

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Karl Aberer, Rémi Philippe Lebret, Negar Foroutan Eghlidi

Vision-Language Pre-training (VLP) has advanced the performance of many visionlanguage tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous w ...

Assoc Computational Linguistics-Acl2023

Modeling Structured Data in Attention-based Models

Alireza Mohammadshahi

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

EPFL2023

Transformer Models for Vision

Jean-Baptiste Francis Marie Juliette Cordonnier

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

EPFL2023

Opportunities, Challenges, and Pitfalls in Making, Characterizing, and Understanding Polymer Brushes

Harm-Anton Klok

Polymer brushes have been theoretically described, their behavior under diverse conditions has been modeled, and their preparation via surface-initiated polymerizations (SIPs) has been progressively refined. However, despite three decades of research endea ...

American Chemical Society2023

Improved framework to estimate travel time and derived distributions in hydrological control volumes

Mitra Asadollahi

Crossing properties of soil saturation, defined as the duration and excursion of soil saturation below and above certain thresholds, are key variables to ecosystem functioning and evolution by primarily influencing the plant and soil microbes physiological ...

EPFL2022

BMAT: An open-source BIDS managing and analysis tool

Meritxell Bach Cuadra, Francesco La Rosa

Magnetic Resonance Imaging (MRI) is an established technique to study in vivo neurological disorders such as Multiple Sclerosis (MS). To avoid errors on MRI data organization and automated processing, a standard called Brain Imaging Data Structure (BIDS) h ...

ELSEVIER SCI LTD2022

Biochemistry of Aminoacyl tRNA Synthetase and tRNAs and Their Engineering for Cell-Free and Synthetic Cell Applications

Sebastian Maerkl, Ragunathan Bava Ganesh

Cell-free biology is increasingly utilized for engineering biological systems, incorporating novel functionality, and circumventing many of the complications associated with cells. The central dogma describes the information flow in biology consisting of t ...

FRONTIERS MEDIA SA2022

V-ATPase/TORC1-mediated ATFS-1 translation directs mitochondrial UPR activation in C. elegans

Johan Auwerx, Kristina Schoonjans, Felix Naef, Xiaoxu Li, Yang Li, Hao Li, Jia Liu, Yan Liu, Wen Gao, Amélia Lalou, Nagammal Neelagandan

To adapt mitochondrial function to the ever-changing intra- and extracellular environment, multiple mitochondrial stress response (MSR) pathways, including the mitochondrial unfolded protein response (UPRmt), have evolved. However, how the mitochondrial st ...

Rockefeller University Press2022

Discourse Phenomena in Machine Translation

Lesly Sadiht Miculicich Werlen

Machine Translation (MT) has made considerable progress in the past two decades, particularly after the introduction of neural network models (NMT). During this time, the research community has mostly focused on modeling and evaluating MT systems at the se ...

EPFL2021

Subword Mapping and Anchoring across Languages

Andrei Popescu-Belis, Georgios Vernikos

State-of-the-art multilingual systems rely on shared vocabularies that sufficiently cover all considered languages. To this end, a simple and frequently used approach makes use of subword vocabularies constructed jointly over several languages. We hypothes ...

Assoc Computational Linguistics-Acl2021

System for planning and/or providing neuromodulation

Grégoire Courtine, Marco Capogrosso, Fabien Bertrand Paul Wagner, Vincent Delattre, Karen Minassian

The present invention relates to systems and methods for planning and/or providing neuromodulation One example system includesa stimulation related basic data storage module for storing stimulation related basic data,a stimulation related response data sto ...

2021

Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images

Devavrat Tomar

Interactive simulation of ultrasound imaging greatly facilitates sonography training. Although ray-tracing based methods have shown promising results, obtaining realistic images requires substantial modeling effort and manual parameter tuning. In addition, ...

Springer2021

Epidemic mitigation by statistical inference from contact tracing data

Lenka Zdeborová, Florent Gérard Krzakala, Maria Refinetti, Indaco Biazzo

Contact tracing is an essential tool to mitigate the impact of a pandemic, such as the COVID-19 pandemic. In order to achieve efficient and scalable contact tracing in real time, digital devices can play an important role. While a lot of attention has been ...

National Academy of Sciences2021

Akt Is S-Palmitoylated: A New Layer of Regulation for Akt

Françoise Gisou van der Goot Grunberg, Laurence Gouzi Abrami

The protein kinase Akt/PKB participates in a great variety of processes, including translation, cell proliferation and survival, as well as malignant transformation and viral infection. In the last few years, novel Akt posttranslational modifications have ...

FRONTIERS MEDIA SA2021

Loss landscape and symmetries in Neural Networks

Mario Geiger

Neural networks (NNs) have been very successful in a variety of tasks ranging from machine translation to image classification. Despite their success, the reasons for their performance are still not well-understood. This thesis explores two main themes: lo ...

EPFL2021

On the ‘cultural transfer’ of modern architecture northwards - Akzeptiere: Das Buch und seine Geschichte

Chiara Monterumisi

"Akzeptiere: Das Buch und seine Geschichte" is the latest in-depth contribution by Atli Magnus Seelow, one of several by him on the 1930 Stockholm exhibition and the book accepetera, the 200-page text often referred to as ‘the manifesto of Swedish function ...

2021

Personalizable computational models of electrical spinal cord stimulation to restore function after neurological disorders

Andreas Rowald

Spinal Cord Injury (SCI) disrupts the communication between the brain and spinal circuits below the lesion, leading to a plethora of neurological impairments, including the loss of motor function. At present, the only medical practices to enhance recovery ...

EPFL2021

From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

Kaicheng Yu

Artificial intelligence has been an ultimate design goal since the inception of computers decades ago. Among the many attempts towards general artificial intelligence, modern machine learning successfully tackles many complex problems thanks to the progres ...

EPFL2021