Subword Mapping and Anchoring across Languages

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

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 ...

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 ...

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 ...

Atypical aspects in speech concern speech that deviates from what is commonly considered normal or healthy. In this thesis, we propose novel methods for detection and analysis of these aspects, e.g. to monitor the temporary state of a speaker, diseases tha ...

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

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 ...

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 ...

Training deep neural network based Automatic Speech Recognition (ASR) models often requires thousands of hours of transcribed data, limiting their use to only a few languages. Moreover, current state-of-the-art acoustic models are based on the Transformer ...

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 ...

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 ...

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 ...

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 ...

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 ...

Most of the Natural Language Processing (NLP) algorithms involve use of distributed vector representations of linguistic units (primarily words and sentences) also known as embeddings in one way or another. These embeddings come in two flavours namely, sta ...

The preparation of parallel corpora is a challenging task, particularly for languages that suffer from under-representation in the digital world. In a multi-lingual country like India, the need for such parallel corpora is stringent for several low-resourc ...

This conversation focuses on the work of Sarah Kenderdine and Merete Sanderhoff, both of whom are based in Europe working on and within museums, as well as playing leadership roles in pan-institutional organisations such as Europeana and the Australasian A ...

Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual textual similarity. In this paper, we concern ourselves with reference-free machine trans ...

Functions of hyperbolic type encode representations on real or complex hyperbolic spaces, usually infinite-dimensional. ...

The present invention relates to a system for planning and/or providing neuromodulation (10), especially neurostimulation, comprising: - first data input module (26) for stimulation related basic data, - a stimulation related basic data storage module (28) ...

The present invention relates to a system for planning and/or providing neuromodulation (10), especially neurostimulation, comprising - a stimulation related basic data storage module (28) for storing the stimulation related basic data, - a stimulation rel ...

Subword Mapping and Anchoring across Languages

Chat with Graph Search

Regularization Techniques for Low-Resource Machine Translation

Dense Image-based Predictions for Comics Analysis

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

Novel Methods For Detection And Analysis Of Atypical Aspects In Speech

Interpretable Representation Learning and Evaluation for Abstractive Summarization

BMAT: An open-source BIDS managing and analysis tool

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

Efficient Transformer-Based Speech Recognition

Discourse Phenomena in Machine Translation

System for planning and/or providing neuromodulation

Loss landscape and symmetries in Neural Networks

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

Epidemic mitigation by statistical inference from contact tracing data

Learning computationally efficient static word and sentence representations

OdiEnCorp 2.0: Odia-English Parallel Corpus for Machine Translation

Sarah Kenderdine + Merete Sanderhoff

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Notes on functions of hyperbolic type

A system for planning and/or providing neuromodulation

A system for planning and/or providing neuromodulation